Tag Archives: algorithms

Technical University of Munich: embedded ethics approach for AI (artificial intelligence) and storing a tv series in synthetic DNA

I stumbled across two news bits of interest from the Technical University of Munich in one day (Sept. 1, 2020, I think). The topics: artificial intelligence (AI) and synthetic DNA (deoxyribonucleic acid).

Embedded ethics and artificial intelligence (AI)

An August 27, 2020 Technical University of Munich (TUM) press release (also on EurekAlert but published Sept. 1, 2020) features information about a proposal to embed ethicists in with AI development teams,

The increasing use of AI (artificial intelligence) in the development of new medical technologies demands greater attention to ethical aspects. An interdisciplinary team at the Technical University of Munich (TUM) advocates the integration of ethics from the very beginning of the development process of new technologies. Alena Buyx, Professor of Ethics in Medicine and Health Technologies, explains the embedded ethics approach.

Professor Buyx, the discussions surrounding a greater emphasis on ethics in AI research have greatly intensified in recent years, to the point where one might speak of “ethics hype” …

Prof. Buyx: … and many committees in Germany and around the world such as the German Ethics Council or the EU Commission High-Level Expert Group on Artificial Intelligence have responded. They are all in agreement: We need more ethics in the development of AI-based health technologies. But how do things look in practice for engineers and designers? Concrete solutions are still few and far between. In a joint pilot project with two Integrative Research Centers at TUM, the Munich School of Robotics and Machine Intelligence (MSRM) with its director, Prof. Sami Haddadin, and the Munich Center for Technology in Society (MCTS), with Prof. Ruth Müller, we want to try out the embedded ethics approach. We published the proposal in Nature Machine Intelligence at the end of July [2020].

What exactly is meant by the “embedded ethics approach”?

Prof.Buyx: The idea is to make ethics an integral part of the research process by integrating ethicists into the AI development team from day one. For example, they attend team meetings on a regular basis and create a sort of “ethical awareness” for certain issues. They also raise and analyze specific ethical and social issues.

Is there an example of this concept in practice?

Prof. Buyx: The Geriatronics Research Center, a flagship project of the MSRM in Garmisch-Partenkirchen, is developing robot assistants to enable people to live independently in old age. The center’s initiatives will include the construction of model apartments designed to try out residential concepts where seniors share their living space with robots. At a joint meeting with the participating engineers, it was noted that the idea of using an open concept layout everywhere in the units – with few doors or individual rooms – would give the robots considerable range of motion. With the seniors, however, this living concept could prove upsetting because they are used to having private spaces. At the outset, the engineers had not given explicit consideration to this aspect.

Prof.Buyx: The approach sounds promising. But how can we avoid “embedded ethics” from turning into an “ethics washing” exercise, offering companies a comforting sense of “being on the safe side” when developing new AI technologies?

That’s not something we can be certain of avoiding. The key is mutual openness and a willingness to listen, with the goal of finding a common language – and subsequently being prepared to effectively implement the ethical aspects. At TUM we are ideally positioned to achieve this. Prof. Sami Haddadin, the director of the MSRM, is also a member of the EU High-Level Group of Artificial Intelligence. In his research, he is guided by the concept of human centered engineering. Consequently, he has supported the idea of embedded ethics from the very beginning. But one thing is certain: Embedded ethics alone will not suddenly make AI “turn ethical”. Ultimately, that will require laws, codes of conduct and possibly state incentives.

Here’s a link to and a citation for the paper espousing the embedded ethics for AI development approach,

An embedded ethics approach for AI development by Stuart McLennan, Amelia Fiske, Leo Anthony Celi, Ruth Müller, Jan Harder, Konstantin Ritt, Sami Haddadin & Alena Buyx. Nature Machine Intelligence (2020) DOI: https://doi.org/10.1038/s42256-020-0214-1 Published 31 July 2020

This paper is behind a paywall.

Religion, ethics and and AI

For some reason embedded ethics and AI got me to thinking about Pope Francis and other religious leaders.

The Roman Catholic Church and AI

There was a recent announcement that the Roman Catholic Church will be working with MicroSoft and IBM on AI and ethics (from a February 28, 2020 article by Jen Copestake for British Broadcasting Corporation (BBC) news online (Note: A link has been removed),

Leaders from the two tech giants met senior church officials in Rome, and agreed to collaborate on “human-centred” ways of designing AI.

Microsoft president Brad Smith admitted some people may “think of us as strange bedfellows” at the signing event.

“But I think the world needs people from different places to come together,” he said.

The call was supported by Pope Francis, in his first detailed remarks about the impact of artificial intelligence on humanity.

The Rome Call for Ethics [sic] was co-signed by Mr Smith, IBM executive vice-president John Kelly and president of the Pontifical Academy for Life Archbishop Vincenzo Paglia.

It puts humans at the centre of new technologies, asking for AI to be designed with a focus on the good of the environment and “our common and shared home and of its human inhabitants”.

Framing the current era as a “renAIssance”, the speakers said the invention of artificial intelligence would be as significant to human development as the invention of the printing press or combustion engine.

UN Food and Agricultural Organization director Qu Dongyu and Italy’s technology minister Paola Pisano were also co-signatories.

Hannah Brockhaus’s February 28, 2020 article for the Catholic News Agency provides some details missing from the BBC report and I found it quite helpful when trying to understand the various pieces that make up this initiative,

The Pontifical Academy for Life signed Friday [February 28, 2020], alongside presidents of IBM and Microsoft, a call for ethical and responsible use of artificial intelligence technologies.

According to the document, “the sponsors of the call express their desire to work together, in this context and at a national and international level, to promote ‘algor-ethics.’”

“Algor-ethics,” according to the text, is the ethical use of artificial intelligence according to the principles of transparency, inclusion, responsibility, impartiality, reliability, security, and privacy.

The signing of the “Rome Call for AI Ethics [PDF]” took place as part of the 2020 assembly of the Pontifical Academy for Life, which was held Feb. 26-28 [2020] on the theme of artificial intelligence.

One part of the assembly was dedicated to private meetings of the academics of the Pontifical Academy for Life. The second was a workshop on AI and ethics that drew 356 participants from 41 countries.

On the morning of Feb. 28 [2020], a public event took place called “renAIssance. For a Humanistic Artificial Intelligence” and included the signing of the AI document by Microsoft President Brad Smith, and IBM Executive Vice-president John Kelly III.

The Director General of FAO, Dongyu Qu, and politician Paola Pisano, representing the Italian government, also signed.

The president of the European Parliament, David Sassoli, was also present Feb. 28.

Pope Francis canceled his scheduled appearance at the event due to feeling unwell. His prepared remarks were read by Archbishop Vincenzo Paglia, president of the Academy for Life.

You can find Pope Francis’s comments about the document here (if you’re not comfortable reading Italian, hopefully, the English translation which follows directly afterward will be helpful). The Pope’s AI initiative has a dedicated website, Rome Call for AI ethics, and while most of the material dates from the February 2020 announcement, they are keeping up a blog. It has two entries, one dated in May 2020 and another in September 2020.

Buddhism and AI

The Dalai Lama is well known for having an interest in science and having hosted scientists for various dialogues. So, I was able to track down a November 10, 2016 article by Ariel Conn for the futureoflife.org website, which features his insights on the matter,

The question of what it means and what it takes to feel needed is an important problem for ethicists and philosophers, but it may be just as important for AI researchers to consider. The Dalai Lama argues that lack of meaning and purpose in one’s work increases frustration and dissatisfaction among even those who are gainfully employed.

“The problem,” says the Dalai Lama, “is … the growing number of people who feel they are no longer useful, no longer needed, no longer one with their societies. … Feeling superfluous is a blow to the human spirit. It leads to social isolation and emotional pain, and creates the conditions for negative emotions to take root.”

If feeling needed and feeling useful are necessary for happiness, then AI researchers may face a conundrum. Many researchers hope that job loss due to artificial intelligence and automation could, in the end, provide people with more leisure time to pursue enjoyable activities. But if the key to happiness is feeling useful and needed, then a society without work could be just as emotionally challenging as today’s career-based societies, and possibly worse.

I also found a talk on the topic by The Venerable Tenzin Priyadarshi, first here’s a description from his bio at the Dalai Lama Center for Ethics and Transformative Values webspace on the Massachusetts Institute of Technology (MIT) website,

… an innovative thinker, philosopher, educator and a polymath monk. He is Director of the Ethics Initiative at the MIT Media Lab and President & CEO of The Dalai Lama Center for Ethics and Transformative Values at the Massachusetts Institute of Technology. Venerable Tenzin’s unusual background encompasses entering a Buddhist monastery at the age of ten and receiving graduate education at Harvard University with degrees ranging from Philosophy to Physics to International Relations. He is a Tribeca Disruptive Fellow and a Fellow at the Center for Advanced Study in Behavioral Sciences at Stanford University. Venerable Tenzin serves on the boards of a number of academic, humanitarian, and religious organizations. He is the recipient of several recognitions and awards and received Harvard’s Distinguished Alumni Honors for his visionary contributions to humanity.

He gave the 2018 Roger W. Heyns Lecture in Religion and Society at Stanford University on the topic, “Religious and Ethical Dimensions of Artificial Intelligence.” The video runs over one hour but he is a sprightly speaker (in comparison to other Buddhist speakers I’ve listened to over the years).

Judaism, Islam, and other Abrahamic faiths examine AI and ethics

I was delighted to find this January 30, 2020 Artificial Intelligence: Implications for Ethics and Religion event as it brought together a range of thinkers from various faiths and disciplines,

New technologies are transforming our world every day, and the pace of change is only accelerating.  In coming years, human beings will create machines capable of out-thinking us and potentially taking on such uniquely-human traits as empathy, ethical reasoning, perhaps even consciousness.  This will have profound implications for virtually every human activity, as well as the meaning we impart to life and creation themselves.  This conference will provide an introduction for non-specialists to Artificial Intelligence (AI):

What is it?  What can it do and be used for?  And what will be its implications for choice and free will; economics and worklife; surveillance economies and surveillance states; the changing nature of facts and truth; and the comparative intelligence and capabilities of humans and machines in the future? 

Leading practitioners, ethicists and theologians will provide cross-disciplinary and cross-denominational perspectives on such challenges as technology addiction, inherent biases and resulting inequalities, the ethics of creating destructive technologies and of turning decision-making over to machines from self-driving cars to “autonomous weapons” systems in warfare, and how we should treat the suffering of “feeling” machines.  The conference ultimately will address how we think about our place in the universe and what this means for both religious thought and theological institutions themselves.

UTS [Union Theological Seminary] is the oldest independent seminary in the United States and has long been known as a bastion of progressive Christian scholarship.  JTS [Jewish Theological Seminary] is one of the academic and spiritual centers of Conservative Judaism and a major center for academic scholarship in Jewish studies. The Riverside Church is an interdenominational, interracial, international, open, welcoming, and affirming church and congregation that has served as a focal point of global and national activism for peace and social justice since its inception and continues to serve God through word and public witness. The annual Greater Good Gathering, the following week at Columbia University’s School of International & Public Affairs, focuses on how technology is changing society, politics and the economy – part of a growing nationwide effort to advance conversations promoting the “greater good.”

They have embedded a video of the event (it runs a little over seven hours) on the January 30, 2020 Artificial Intelligence: Implications for Ethics and Religion event page. For anyone who finds that a daunting amount of information, you may want to check out the speaker list for ideas about who might be writing and thinking on this topic.

As for Islam, I did track down this November 29, 2018 article by Shahino Mah Abdullah, a fellow at the Institute of Advanced Islamic Studies (IAIS) Malaysia,

As the global community continues to work together on the ethics of AI, there are still vast opportunities to offer ethical inputs, including the ethical principles based on Islamic teachings.

This is in line with Islam’s encouragement for its believers to convey beneficial messages, including to share its ethical principles with society.

In Islam, ethics or akhlak (virtuous character traits) in Arabic, is sometimes employed interchangeably in the Arabic language with adab, which means the manner, attitude, behaviour, and etiquette of putting things in their proper places. Islamic ethics cover all the legal concepts ranging from syariah (Islamic law), fiqh ( jurisprudence), qanun (ordinance), and ‘urf (customary practices).

Adopting and applying moral values based on the Islamic ethical concept or applied Islamic ethics could be a way to address various issues in today’s societies.

At the same time, this approach is in line with the higher objectives of syariah (maqasid alsyariah) that is aimed at conserving human benefit by the protection of human values, including faith (hifz al-din), life (hifz alnafs), lineage (hifz al-nasl), intellect (hifz al-‘aql), and property (hifz al-mal). This approach could be very helpful to address contemporary issues, including those related to the rise of AI and intelligent robots.

..

Part of the difficulty with tracking down more about AI, ethics, and various religions is linguistic. I simply don’t have the language skills to search for the commentaries and, even in English, I may not have the best or most appropriate search terms.

Television (TV) episodes stored on DNA?

According to a Sept. 1, 2020 news item on Nanowerk, the first episode of a tv series, ‘Biohackers’ has been stored on synthetic DNA (deoxyribonucleic acid) by a researcher at TUM and colleagues at another institution,

The first episode of the newly released series “Biohackers” was stored in the form of synthetic DNA. This was made possible by the research of Prof. Reinhard Heckel of the Technical University of Munich (TUM) and his colleague Prof. Robert Grass of ETH Zürich.

They have developed a method that permits the stable storage of large quantities of data on DNA for over 1000 years.

A Sept. 1, 2020 TUM press release, which originated the news item, proceeds with more detail in an interview format,

Prof. Heckel, Biohackers is about a medical student seeking revenge on a professor with a dark past – and the manipulation of DNA with biotechnology tools. You were commissioned to store the series on DNA. How does that work?

First, I should mention that what we’re talking about is artificially generated – in other words, synthetic – DNA. DNA consists of four building blocks: the nucleotides adenine (A), thymine (T), guanine (G) and cytosine (C). Computer data, meanwhile, are coded as zeros and ones. The first episode of Biohackers consists of a sequence of around 600 million zeros and ones. To code the sequence 01 01 11 00 in DNA, for example, we decide which number combinations will correspond to which letters. For example: 00 is A, 01 is C, 10 is G and 11 is T. Our example then produces the DNA sequence CCTA. Using this principle of DNA data storage, we have stored the first episode of the series on DNA.

And to view the series – is it just a matter of “reverse translation” of the letters?

In a very simplified sense, you can visualize it like that. When writing, storing and reading the DNA, however, errors occur. If these errors are not corrected, the data stored on the DNA will be lost. To solve the problem, I have developed an algorithm based on channel coding. This method involves correcting errors that take place during information transfers. The underlying idea is to add redundancy to the data. Think of language: When we read or hear a word with missing or incorrect letters, the computing power of our brain is still capable of understanding the word. The algorithm follows the same principle: It encodes the data with sufficient redundancy to ensure that even highly inaccurate data can be restored later.

Channel coding is used in many fields, including in telecommunications. What challenges did you face when developing your solution?

The first challenge was to create an algorithm specifically geared to the errors that occur in DNA. The second one was to make the algorithm so efficient that the largest possible quantities of data can be stored on the smallest possible quantity of DNA, so that only the absolutely necessary amount of redundancy is added. We demonstrated that our algorithm is optimized in that sense.

DNA data storage is very expensive because of the complexity of DNA production as well as the reading process. What makes DNA an attractive storage medium despite these challenges?

First, DNA has a very high information density. This permits the storage of enormous data volumes in a minimal space. In the case of the TV series, we stored “only” 100 megabytes on a picogram – or a billionth of a gram of DNA. Theoretically, however, it would be possible to store up to 200 exabytes on one gram of DNA. And DNA lasts a long time. By comparison: If you never turned on your PC or wrote data to the hard disk it contains, the data would disappear after a couple of years. By contrast, DNA can remain stable for many thousands of years if it is packed right.

And the method you have developed also makes the DNA strands durable – practically indestructible.

My colleague Robert Grass was the first to develop a process for the “stable packing” of DNA strands by encapsulating them in nanometer-scale spheres made of silica glass. This ensures that the DNA is protected against mechanical influences. In a joint paper in 2015, we presented the first robust DNA data storage concept with our algorithm and the encapsulation process developed by Prof. Grass. Since then we have continuously improved our method. In our most recent publication in Nature Protocols of January 2020, we passed on what we have learned.

What are your next steps? Does data storage on DNA have a future?

We’re working on a way to make DNA data storage cheaper and faster. “Biohackers” was a milestone en route to commercialization. But we still have a long way to go. If this technology proves successful, big things will be possible. Entire libraries, all movies, photos, music and knowledge of every kind – provided it can be represented in the form of data – could be stored on DNA and would thus be available to humanity for eternity.

Here’s a link to and a citation for the paper,

Reading and writing digital data in DNA by Linda C. Meiser, Philipp L. Antkowiak, Julian Koch, Weida D. Chen, A. Xavier Kohll, Wendelin J. Stark, Reinhard Heckel & Robert N. Grass. Nature Protocols volume 15, pages86–101(2020) Issue Date: January 2020 DOI: https://doi.org/10.1038/s41596-019-0244-5 Published [online] 29 November 2019

This paper is behind a paywall.

As for ‘Biohackers’, it’s a German science fiction television series and you can find out more about it here on the Internet Movie Database.

Data science guide from Sense about Science

Sense about Science, headquartered in the UK, is in its own words (from its homepage)

Sense about Science is an independent campaigning charity that challenges the misrepresentation of science and evidence in public life. …

According to an October 1, 2019 announcement from Sense about Science (received via email), the organization has published a new guide,

Our director warned yesterday [September 30, 2019] that data science is being given a free
pass on quality in too many arenas. From flood predictions to mortgage offers to the prediction of housing needs, we are not asking enough about whether AI solutions and algorithms can bear the weight we want to put on them.

It was the UK launch of our ‘Data Science: a guide for society’ at the Institute of Physics, where we invited representatives from different sectors to take up the challenge of creating a more questioning culture. Tracey Brown said the situation was like medicine 50 years ago: it seems that some people have become too clever to explain and the rest of us are feeling too dumb to ask.

At the end of the event we had a lot of proposals for how to make different communities aware of the guide’s three fundamental questions from the people who attended. There are many hundreds of people among our friends who could do something along these lines:

     * Publicise the guide
     * Incorporate it into your own work
     * Send it to people who are involved in procurement, licensing or
reporting or decision making at community, national and international
levels
     * Undertake a project with us to equip particular groups such as
parliamentary advisers, journalists and small charities.

Would you take a look at the guide [1] here and tell me if there’s something you can do? (alex@senseaboutscience.org)

There are launches planned in other countries over the rest of this year and into 2020. We are drawing up a map of offers to reach different communities. I’ll share all your suggestions with my colleague Errin Riley at the end of this week and we will get back to you quickly.

Before linking you to the guide, here’s a brief description from the Patterns in Data webpage,

In recent years, phrases like ‘big data’, ‘machine learning’, ‘algorithms’ and ‘pattern recognition’ have started slipping into everyday discussion. We’ve worked with researchers and experts to generate an open and informed public discussion on patterns in data across a wide range of projects.

Data Science: A guide for society

According to the headlines, we’re in the middle of a ‘data revolution: large, detailed datasets and complex algorithms allow us to make predictions on anything from who will win the league to who is likely to commit a crime. Our ability to question the quality of evidence – as the public, journalists, politicians or decision makers – needs to be expanded to meet this. To know the questions to ask and how to press for clarity about the strengths and weaknesses of using analysis from data models to make decisions. This is a guide to having more of those conversations, regardless of how much you don’t know about data science.

Here’s Data Science: A Guide for Society.

AI (artificial intelligence) text generator, too dangerous to release?

Could this latest version of OpenAI‘s text generator be so good that it would fool you? And following on that thought could the concomitant reluctance to release the research be real or is it a publicity stunt? Here’s a sample of the text from the GPT2 AI model from a February 15, 2019 article by Mark Fraunfelder for Boing Boing,

Recycling is good for the world.
NO! YOU COULD NOT BE MORE WRONG!!
MODEL COMPLETION (MACHINE-WRITTEN, 25 TRIES)
Recycling is NOT good for the world. It is bad for the environment, it is bad for our health, and it is bad for our economy. I’m not kidding. Recycling is not good for the environment. It is destructive to the earth and it is a major contributor to global warming. Recycling is not good for our health. It contributes to obesity and diseases like heart disease and cancer. Recycling is bad for our economy. It increases the cost of a product, and in turn, the price of everything that is made with that product. Recycling is not good for our nation. We pay a tremendous price for the privilege of having the world’s most advanced and efficient recycling system. Recycling is a huge, colossal waste of time, energy, money, and resources. And THAT is why we need to get back to basics and get back to basics in our recycling efforts. One of the best ways to start is to look at the process of creating a paper product. When you make a paper product, it is basically a long chain of materials. Everything from the raw materials (wood, cardboard, paper, etc.), to the reagents (dyes, solvents, etc.) to the printing equipment (chemicals, glue, paper, ink, etc.), to the packaging, to the packaging materials (mercury, chemicals, etc.) to the processing equipment (heating, cooling, etc.), to the packaging materials, to the packaging materials that are shipped overseas and to the packaging materials that are used in the United States. Each step along the way creates tons of waste that we constantly have to clean up. The process of making a paper product is a very wasteful one. But the end result is something that all of us need to consume. And if we want to keep the recycling process running efficiently, then we really need to think about each and every step that goes into making a paper product.

The first few sentences don’t work for me but once the discussion turns to making paper products, then it becomes more convincing to me. As to whether the company’s reluctance to release the research is genuine or a publicity stunt, I don’t know. However, there was a fair degree of interest in GPT2 after the decision.

From a February 14, 2019 article by Alex Hern for the Guardian,

OpenAI, an nonprofit research company backed by Elon Musk, Reid Hoffman, Sam Altman, and others, says its new AI model, called GPT2 is so good and the risk of malicious use so high that it is breaking from its normal practice of releasing the full research to the public in order to allow more time to discuss the ramifications of the technological breakthrough.

At its core, GPT2 is a text generator. The AI system is fed text, anything from a few words to a whole page, and asked to write the next few sentences based on its predictions of what should come next. The system is pushing the boundaries of what was thought possible, both in terms of the quality of the output, and the wide variety of potential uses.

When used to simply generate new text, GPT2 is capable of writing plausible passages that match what it is given in both style and subject. It rarely shows any of the quirks that mark out previous AI systems, such as forgetting what it is writing about midway through a paragraph, or mangling the syntax of long sentences.

Feed it the opening line of George Orwell’s Nineteen Eighty-Four – “It was a bright cold day in April, and the clocks were striking thirteen” – and the system recognises the vaguely futuristic tone and the novelistic style, and continues with: …

Sean Gallagher’s February 15, 2019 posting on the ars Technica blog provides some insight that’s partially written a style sometimes associated with gossip (Note: Links have been removed),

OpenAI is funded by contributions from a group of technology executives and investors connected to what some have referred to as the PayPal “mafia”—Elon Musk, Peter Thiel, Jessica Livingston, and Sam Altman of YCombinator, former PayPal COO and LinkedIn co-founder Reid Hoffman, and former Stripe Chief Technology Officer Greg Brockman. [emphasis mine] Brockman now serves as OpenAI’s CTO. Musk has repeatedly warned of the potential existential dangers posed by AI, and OpenAI is focused on trying to shape the future of artificial intelligence technology—ideally moving it away from potentially harmful applications.

Given present-day concerns about how fake content has been used to both generate money for “fake news” publishers and potentially spread misinformation and undermine public debate, GPT-2’s output certainly qualifies as concerning. Unlike other text generation “bot” models, such as those based on Markov chain algorithms, the GPT-2 “bot” did not lose track of what it was writing about as it generated output, keeping everything in context.

For example: given a two-sentence entry, GPT-2 generated a fake science story on the discovery of unicorns in the Andes, a story about the economic impact of Brexit, a report about a theft of nuclear materials near Cincinnati, a story about Miley Cyrus being caught shoplifting, and a student’s report on the causes of the US Civil War.

Each matched the style of the genre from the writing prompt, including manufacturing quotes from sources. In other samples, GPT-2 generated a rant about why recycling is bad, a speech written by John F. Kennedy’s brain transplanted into a robot (complete with footnotes about the feat itself), and a rewrite of a scene from The Lord of the Rings.

While the model required multiple tries to get a good sample, GPT-2 generated “good” results based on “how familiar the model is with the context,” the researchers wrote. “When prompted with topics that are highly represented in the data (Brexit, Miley Cyrus, Lord of the Rings, and so on), it seems to be capable of generating reasonable samples about 50 percent of the time. The opposite is also true: on highly technical or esoteric types of content, the model can perform poorly.”

There were some weak spots encountered in GPT-2’s word modeling—for example, the researchers noted it sometimes “writes about fires happening under water.” But the model could be fine-tuned to specific tasks and perform much better. “We can fine-tune GPT-2 on the Amazon Reviews dataset and use this to let us write reviews conditioned on things like star rating and category,” the authors explained.

James Vincent’s February 14, 2019 article for The Verge offers a deeper dive into the world of AI text agents and what makes GPT2 so special (Note: Links have been removed),

For decades, machines have struggled with the subtleties of human language, and even the recent boom in deep learning powered by big data and improved processors has failed to crack this cognitive challenge. Algorithmic moderators still overlook abusive comments, and the world’s most talkative chatbots can barely keep a conversation alive. But new methods for analyzing text, developed by heavyweights like Google and OpenAI as well as independent researchers, are unlocking previously unheard-of talents.

OpenAI’s new algorithm, named GPT-2, is one of the most exciting examples yet. It excels at a task known as language modeling, which tests a program’s ability to predict the next word in a given sentence. Give it a fake headline, and it’ll write the rest of the article, complete with fake quotations and statistics. Feed it the first line of a short story, and it’ll tell you what happens to your character next. It can even write fan fiction, given the right prompt.

The writing it produces is usually easily identifiable as non-human. Although its grammar and spelling are generally correct, it tends to stray off topic, and the text it produces lacks overall coherence. But what’s really impressive about GPT-2 is not its fluency but its flexibility.

This algorithm was trained on the task of language modeling by ingesting huge numbers of articles, blogs, and websites. By using just this data — and with no retooling from OpenAI’s engineers — it achieved state-of-the-art scores on a number of unseen language tests, an achievement known as “zero-shot learning.” It can also perform other writing-related tasks, like translating text from one language to another, summarizing long articles, and answering trivia questions.

GPT-2 does each of these jobs less competently than a specialized system, but its flexibility is a significant achievement. Nearly all machine learning systems used today are “narrow AI,” meaning they’re able to tackle only specific tasks. DeepMind’s original AlphaGo program, for example, was able to beat the world’s champion Go player, but it couldn’t best a child at Monopoly. The prowess of GPT-2, say OpenAI, suggests there could be methods available to researchers right now that can mimic more generalized brainpower.

“What the new OpenAI work has shown is that: yes, you absolutely can build something that really seems to ‘understand’ a lot about the world, just by having it read,” says Jeremy Howard, a researcher who was not involved with OpenAI’s work but has developed similar language modeling programs …

To put this work into context, it’s important to understand how challenging the task of language modeling really is. If I asked you to predict the next word in a given sentence — say, “My trip to the beach was cut short by bad __” — your answer would draw upon on a range of knowledge. You’d consider the grammar of the sentence and its tone but also your general understanding of the world. What sorts of bad things are likely to ruin a day at the beach? Would it be bad fruit, bad dogs, or bad weather? (Probably the latter.)

Despite this, programs that perform text prediction are quite common. You’ve probably encountered one today, in fact, whether that’s Google’s AutoComplete feature or the Predictive Text function in iOS. But these systems are drawing on relatively simple types of language modeling, while algorithms like GPT-2 encode the same information in more complex ways.

The difference between these two approaches is technically arcane, but it can be summed up in a single word: depth. Older methods record information about words in only their most obvious contexts, while newer methods dig deeper into their multiple meanings.

So while a system like Predictive Text only knows that the word “sunny” is used to describe the weather, newer algorithms know when “sunny” is referring to someone’s character or mood, when “Sunny” is a person, or when “Sunny” means the 1976 smash hit by Boney M.

The success of these newer, deeper language models has caused a stir in the AI community. Researcher Sebastian Ruder compares their success to advances made in computer vision in the early 2010s. At this time, deep learning helped algorithms make huge strides in their ability to identify and categorize visual data, kickstarting the current AI boom. Without these advances, a whole range of technologies — from self-driving cars to facial recognition and AI-enhanced photography — would be impossible today. This latest leap in language understanding could have similar, transformational effects.

Hern’s article for the Guardian (February 14, 2019 article ) acts as a good overview, while Gallagher’s ars Technical posting (February 15, 2019 posting) and Vincent’s article (February 14, 2019 article) for the The Verge take you progressively deeper into the world of AI text agents.

For anyone who wants to dig down even further, there’s a February 14, 2019 posting on OpenAI’s blog.

Robot radiologists (artificially intelligent doctors)

Mutaz Musa, a physician at New York Presbyterian Hospital/Weill Cornell (Department of Emergency Medicine) and software developer in New York City, has penned an eyeopening opinion piece about artificial intelligence (or robots if you prefer) and the field of radiology. From a June 25, 2018 opinion piece for The Scientist (Note: Links have been removed),

Although artificial intelligence has raised fears of job loss for many, we doctors have thus far enjoyed a smug sense of security. There are signs, however, that the first wave of AI-driven redundancies among doctors is fast approaching. And radiologists seem to be first on the chopping block.

Andrew Ng, founder of online learning platform Coursera and former CTO of “China’s Google,” Baidu, recently announced the development of CheXNet, a convolutional neural net capable of recognizing pneumonia and other thoracic pathologies on chest X-rays better than human radiologists. Earlier this year, a Hungarian group developed a similar system for detecting and classifying features of breast cancer in mammograms. In 2017, Adelaide University researchers published details of a bot capable of matching human radiologist performance in detecting hip fractures. And, of course, Google achieved superhuman proficiency in detecting diabetic retinopathy in fundus photographs, a task outside the scope of most radiologists.

Beyond single, two-dimensional radiographs, a team at Oxford University developed a system for detecting spinal disease from MRI data with a performance equivalent to a human radiologist. Meanwhile, researchers at the University of California, Los Angeles, reported detecting pathology on head CT scans with an error rate more than 20 times lower than a human radiologist.

Although these particular projects are still in the research phase and far from perfect—for instance, often pitting their machines against a limited number of radiologists—the pace of progress alone is telling.

Others have already taken their algorithms out of the lab and into the marketplace. Enlitic, founded by Aussie serial entrepreneur and University of San Francisco researcher Jeremy Howard, is a Bay-Area startup that offers automated X-ray and chest CAT scan interpretation services. Enlitic’s systems putatively can judge the malignancy of nodules up to 50 percent more accurately than a panel of radiologists and identify fractures so small they’d typically be missed by the human eye. One of Enlitic’s largest investors, Capitol Health, owns a network of diagnostic imaging centers throughout Australia, anticipating the broad rollout of this technology. Another Bay-Area startup, Arterys, offers cloud-based medical imaging diagnostics. Arterys’s services extend beyond plain films to cardiac MRIs and CAT scans of the chest and abdomen. And there are many others.

Musa has offered a compelling argument with lots of links to supporting evidence.

[downloaded from https://www.the-scientist.com/news-opinion/opinion–rise-of-the-robot-radiologists-64356]

And evidence keeps mounting, I just stumbled across this June 30, 2018 news item on Xinhuanet.com,

An artificial intelligence (AI) system scored 2:0 against elite human physicians Saturday in two rounds of competitions in diagnosing brain tumors and predicting hematoma expansion in Beijing.

The BioMind AI system, developed by the Artificial Intelligence Research Centre for Neurological Disorders at the Beijing Tiantan Hospital and a research team from the Capital Medical University, made correct diagnoses in 87 percent of 225 cases in about 15 minutes, while a team of 15 senior doctors only achieved 66-percent accuracy.

The AI also gave correct predictions in 83 percent of brain hematoma expansion cases, outperforming the 63-percent accuracy among a group of physicians from renowned hospitals across the country.

The outcomes for human physicians were quite normal and even better than the average accuracy in ordinary hospitals, said Gao Peiyi, head of the radiology department at Tiantan Hospital, a leading institution on neurology and neurosurgery.

To train the AI, developers fed it tens of thousands of images of nervous system-related diseases that the Tiantan Hospital has archived over the past 10 years, making it capable of diagnosing common neurological diseases such as meningioma and glioma with an accuracy rate of over 90 percent, comparable to that of a senior doctor.

All the cases were real and contributed by the hospital, but never used as training material for the AI, according to the organizer.

Wang Yongjun, executive vice president of the Tiantan Hospital, said that he personally did not care very much about who won, because the contest was never intended to pit humans against technology but to help doctors learn and improve [emphasis mine] through interactions with technology.

“I hope through this competition, doctors can experience the power of artificial intelligence. This is especially so for some doctors who are skeptical about artificial intelligence. I hope they can further understand AI and eliminate their fears toward it,” said Wang.

Dr. Lin Yi who participated and lost in the second round, said that she welcomes AI, as it is not a threat but a “friend.” [emphasis mine]

AI will not only reduce the workload but also push doctors to keep learning and improve their skills, said Lin.

Bian Xiuwu, an academician with the Chinese Academy of Science and a member of the competition’s jury, said there has never been an absolute standard correct answer in diagnosing developing diseases, and the AI would only serve as an assistant to doctors in giving preliminary results. [emphasis mine]

Dr. Paul Parizel, former president of the European Society of Radiology and another member of the jury, also agreed that AI will not replace doctors, but will instead function similar to how GPS does for drivers. [emphasis mine]

Dr. Gauden Galea, representative of the World Health Organization in China, said AI is an exciting tool for healthcare but still in the primitive stages.

Based on the size of its population and the huge volume of accessible digital medical data, China has a unique advantage in developing medical AI, according to Galea.

China has introduced a series of plans in developing AI applications in recent years.

In 2017, the State Council issued a development plan on the new generation of Artificial Intelligence and the Ministry of Industry and Information Technology also issued the “Three-Year Action Plan for Promoting the Development of a New Generation of Artificial Intelligence (2018-2020).”

The Action Plan proposed developing medical image-assisted diagnostic systems to support medicine in various fields.

I note the reference to cars and global positioning systems (GPS) and their role as ‘helpers’;, it seems no one at the ‘AI and radiology’ competition has heard of driverless cars. Here’s Musa on those reassuring comments abut how the technology won’t replace experts but rather augment their skills,

To be sure, these services frame themselves as “support products” that “make doctors faster,” rather than replacements that make doctors redundant. This language may reflect a reserved view of the technology, though it likely also represents a marketing strategy keen to avoid threatening or antagonizing incumbents. After all, many of the customers themselves, for now, are radiologists.

Radiology isn’t the only area where experts might find themselves displaced.

Eye experts

It seems inroads have been made by artificial intelligence systems (AI) into the diagnosis of eye diseases. It got the ‘Fast Company’ treatment (exciting new tech, learn all about it) as can be seen further down in this posting. First, here’s a more restrained announcement, from an August 14, 2018 news item on phys.org (Note: A link has been removed),

An artificial intelligence (AI) system, which can recommend the correct referral decision for more than 50 eye diseases, as accurately as experts has been developed by Moorfields Eye Hospital NHS Foundation Trust, DeepMind Health and UCL [University College London].

The breakthrough research, published online by Nature Medicine, describes how machine-learning technology has been successfully trained on thousands of historic de-personalised eye scans to identify features of eye disease and recommend how patients should be referred for care.

Researchers hope the technology could one day transform the way professionals carry out eye tests, allowing them to spot conditions earlier and prioritise patients with the most serious eye diseases before irreversible damage sets in.

An August 13, 2018 UCL press release, which originated the news item, describes the research and the reasons behind it in more detail,

More than 285 million people worldwide live with some form of sight loss, including more than two million people in the UK. Eye diseases remain one of the biggest causes of sight loss, and many can be prevented with early detection and treatment.

Dr Pearse Keane, NIHR Clinician Scientist at the UCL Institute of Ophthalmology and consultant ophthalmologist at Moorfields Eye Hospital NHS Foundation Trust said: “The number of eye scans we’re performing is growing at a pace much faster than human experts are able to interpret them. There is a risk that this may cause delays in the diagnosis and treatment of sight-threatening diseases, which can be devastating for patients.”

“The AI technology we’re developing is designed to prioritise patients who need to be seen and treated urgently by a doctor or eye care professional. If we can diagnose and treat eye conditions early, it gives us the best chance of saving people’s sight. With further research it could lead to greater consistency and quality of care for patients with eye problems in the future.”

The study, launched in 2016, brought together leading NHS eye health professionals and scientists from UCL and the National Institute for Health Research (NIHR) with some of the UK’s top technologists at DeepMind to investigate whether AI technology could help improve the care of patients with sight-threatening diseases, such as age-related macular degeneration and diabetic eye disease.

Using two types of neural network – mathematical systems for identifying patterns in images or data – the AI system quickly learnt to identify 10 features of eye disease from highly complex optical coherence tomography (OCT) scans. The system was then able to recommend a referral decision based on the most urgent conditions detected.

To establish whether the AI system was making correct referrals, clinicians also viewed the same OCT scans and made their own referral decisions. The study concluded that AI was able to make the right referral recommendation more than 94% of the time, matching the performance of expert clinicians.

The AI has been developed with two unique features which maximise its potential use in eye care. Firstly, the system can provide information that helps explain to eye care professionals how it arrives at its recommendations. This information includes visuals of the features of eye disease it has identified on the OCT scan and the level of confidence the system has in its recommendations, in the form of a percentage. This functionality is crucial in helping clinicians scrutinise the technology’s recommendations and check its accuracy before deciding the type of care and treatment a patient receives.

Secondly, the AI system can be easily applied to different types of eye scanner, not just the specific model on which it was trained. This could significantly increase the number of people who benefit from this technology and future-proof it, so it can still be used even as OCT scanners are upgraded or replaced over time.

The next step is for the research to go through clinical trials to explore how this technology might improve patient care in practice, and regulatory approval before it can be used in hospitals and other clinical settings.

If clinical trials are successful in demonstrating that the technology can be used safely and effectively, Moorfields will be able to use an eventual, regulatory-approved product for free, across all 30 of their UK hospitals and community clinics, for an initial period of five years.

The work that has gone into this project will also help accelerate wider NHS research for many years to come. For example, DeepMind has invested significant resources to clean, curate and label Moorfields’ de-identified research dataset to create one of the most advanced eye research databases in the world.

Moorfields owns this database as a non-commercial public asset, which is already forming the basis of nine separate medical research studies. In addition, Moorfields can also use DeepMind’s trained AI model for future non-commercial research efforts, which could help advance medical research even further.

Mustafa Suleyman, Co-founder and Head of Applied AI at DeepMind Health, said: “We set up DeepMind Health because we believe artificial intelligence can help solve some of society’s biggest health challenges, like avoidable sight loss, which affects millions of people across the globe. These incredibly exciting results take us one step closer to that goal and could, in time, transform the diagnosis, treatment and management of patients with sight threatening eye conditions, not just at Moorfields, but around the world.”

Professor Sir Peng Tee Khaw, director of the NIHR Biomedical Research Centre at Moorfields Eye Hospital NHS Foundation Trust and UCL Institute of Ophthalmology said: “The results of this pioneering research with DeepMind are very exciting and demonstrate the potential sight-saving impact AI could have for patients. I am in no doubt that AI has a vital role to play in the future of healthcare, particularly when it comes to training and helping medical professionals so that patients benefit from vital treatment earlier than might previously have been possible. This shows the transformative research than can be carried out in the UK combining world leading industry and NIHR/NHS hospital/university partnerships.”

Matt Hancock, Health and Social Care Secretary, said: “This is hugely exciting and exactly the type of technology which will benefit the NHS in the long term and improve patient care – that’s why we fund over a billion pounds a year in health research as part of our long term plan for the NHS.”

Here’s a link to and a citation for the study,

Clinically applicable deep learning for diagnosis and referral in retinal disease by Jeffrey De Fauw, Joseph R. Ledsam, Bernardino Romera-Paredes, Stanislav Nikolov, Nenad Tomasev, Sam Blackwell, Harry Askham, Xavier Glorot, Brendan O’Donoghue, Daniel Visentin, George van den Driessche, Balaji Lakshminarayanan, Clemens Meyer, Faith Mackinder, Simon Bouton, Kareem Ayoub, Reena Chopra, Dominic King, Alan Karthikesalingam, Cían O. Hughes, Rosalind Raine, Julian Hughes, Dawn A. Sim, Catherine Egan, Adnan Tufail, Hugh Montgomery, Demis Hassabis, Geraint Rees, Trevor Back, Peng T. Khaw, Mustafa Suleyman, Julien Cornebise, Pearse A. Keane, & Olaf Ronneberger. Nature Medicine (2018) DOI: https://doi.org/10.1038/s41591-018-0107-6 Published 13 August 2018

This paper is behind a paywall.

And now, Melissa Locker’s August 15, 2018 article for Fast Company (Note: Links have been removed),

In a paper published in Nature Medicine on Monday, Google’s DeepMind subsidiary, UCL, and researchers at Moorfields Eye Hospital showed off their new AI system. The researchers used deep learning to create algorithm-driven software that can identify common patterns in data culled from dozens of common eye diseases from 3D scans. The result is an AI that can identify more than 50 diseases with incredible accuracy and can then refer patients to a specialist. Even more important, though, is that the AI can explain why a diagnosis was made, indicating which part of the scan prompted the outcome. It’s an important step in both medicine and in making AIs slightly more human

The editor or writer has even highlighted the sentence about the system’s accuracy—not just good but incredible!

I will be publishing something soon [my August 21, 2018 posting] which highlights some of the questions one might want to ask about AI and medicine before diving headfirst into this brave new world of medicine.

AI x 2: the Amnesty International and Artificial Intelligence story

Amnesty International and artificial intelligence seem like an unexpected combination but it all makes sense when you read a June 13, 2018 article by Steven Melendez for Fast Company (Note: Links have been removed),

If companies working on artificial intelligence don’t take steps to safeguard human rights, “nightmare scenarios” could unfold, warns Rasha Abdul Rahim, an arms control and artificial intelligence researcher at Amnesty International in a blog post. Those scenarios could involve armed, autonomous systems choosing military targets with little human oversight, or discrimination caused by biased algorithms, she warns.

Rahim pointed at recent reports of Google’s involvement in the Pentagon’s Project Maven, which involves harnessing AI image recognition technology to rapidly process photos taken by drones. Google recently unveiled new AI ethics policies and has said it won’t continue with the project once its current contract expires next year after high-profile employee dissent over the project. …

“Compliance with the laws of war requires human judgement [sic] –the ability to analyze the intentions behind actions and make complex decisions about the proportionality or necessity of an attack,” Rahim writes. “Machines and algorithms cannot recreate these human skills, and nor can they negotiate, produce empathy, or respond to unpredictable situations. In light of these risks, Amnesty International and its partners in the Campaign to Stop Killer Robots are calling for a total ban on the development, deployment, and use of fully autonomous weapon systems.”

Rasha Abdul Rahim’s June 14, 2018 posting (I’m putting the discrepancy in publication dates down to timezone differences) on the Amnesty International website (Note: Links have been removed),

Last week [June 7, 2018] Google released a set of principles to govern its development of AI technologies. They include a broad commitment not to design or deploy AI in weaponry, and come in the wake of the company’s announcement that it will not renew its existing contract for Project Maven, the US Department of Defense’s AI initiative, when it expires in 2019.

The fact that Google maintains its existing Project Maven contract for now raises an important question. Does Google consider that continuing to provide AI technology to the US government’s drone programme is in line with its new principles? Project Maven is a litmus test that allows us to see what Google’s new principles mean in practice.

As details of the US drone programme are shrouded in secrecy, it is unclear precisely what role Google plays in Project Maven. What we do know is that US drone programme, under successive administrations, has been beset by credible allegations of unlawful killings and civilian casualties. The cooperation of Google, in any capacity, is extremely troubling and could potentially implicate it in unlawful strikes.

As AI technology advances, the question of who will be held accountable for associated human rights abuses is becoming increasingly urgent. Machine learning, and AI more broadly, impact a range of human rights including privacy, freedom of expression and the right to life. It is partly in the hands of companies like Google to safeguard these rights in relation to their operations – for us and for future generations. If they don’t, some nightmare scenarios could unfold.

Warfare has already changed dramatically in recent years – a couple of decades ago the idea of remote controlled bomber planes would have seemed like science fiction. While the drones currently in use are still controlled by humans, China, France, Israel, Russia, South Korea, the UK and the US are all known to be developing military robots which are getting smaller and more autonomous.

For example, the UK is developing a number of autonomous systems, including the BAE [Systems] Taranis, an unmanned combat aircraft system which can fly in autonomous mode and automatically identify a target within a programmed area. Kalashnikov, the Russian arms manufacturer, is developing a fully automated, high-calibre gun that uses artificial neural networks to choose targets. The US Army Research Laboratory in Maryland, in collaboration with BAE Systems and several academic institutions, has been developing micro drones which weigh less than 30 grams, as well as pocket-sized robots that can hop or crawl.

Of course, it’s not just in conflict zones that AI is threatening human rights. Machine learning is already being used by governments in a wide range of contexts that directly impact people’s lives, including policing [emphasis mine], welfare systems, criminal justice and healthcare. Some US courts use algorithms to predict future behaviour of defendants and determine their sentence lengths accordingly. The potential for this approach to reinforce power structures, discrimination or inequalities is huge.

In july 2017, the Vancouver Police Department announced its use of predictive policing software, the first such jurisdiction in Canada to make use of the technology. My Nov. 23, 2017 posting featured the announcement.

The almost too aptly named Campaign to Stop Killer Robots can be found here. Their About Us page provides a brief history,

Formed by the following non-governmental organizations (NGOs) at a meeting in New York on 19 October 2012 and launched in London in April 2013, the Campaign to Stop Killer Robots is an international coalition working to preemptively ban fully autonomous weapons. See the Chronology charting our major actions and achievements to date.

Steering Committee

The Steering Committee is the campaign’s principal leadership and decision-making body. It is comprised of five international NGOs, a regional NGO network, and four national NGOs that work internationally:

Human Rights Watch
Article 36
Association for Aid and Relief Japan
International Committee for Robot Arms Control
Mines Action Canada
Nobel Women’s Initiative
PAX (formerly known as IKV Pax Christi)
Pugwash Conferences on Science & World Affairs
Seguridad Humana en América Latina y el Caribe (SEHLAC)
Women’s International League for Peace and Freedom

For more information, see this Overview. A Terms of Reference is also available on request, detailing the committee’s selection process, mandate, decision-making, meetings and communication, and expected commitments.

For anyone who may be interested in joining Amnesty International, go here.

Yes! Art, genetic modifications, gene editing, and xenotransplantation at the Vancouver Biennale (Canada)

Patricia Piccinini’s Curious Imaginings Courtesy: Vancouver Biennale [downloaded from http://dailyhive.com/vancouver/vancouver-biennale-unsual-public-art-2018/]

Up to this point, I’ve been a little jealous of the Art/Sci Salon’s (Toronto, Canada) January 2018 workshops for artists and discussions about CRISPR ((clustered regularly interspaced short palindromic repeats))/Cas9 and its social implications. (See my January 10, 2018 posting for more about the events.) Now, it seems Vancouver may be in line for its ‘own’ discussion about CRISPR and the implications of gene editing. The image you saw (above) represents one of the installations being hosted by the 2018 – 2020 edition of the Vancouver Biennale.

While this posting is mostly about the Biennale and Piccinini’s work, there is a ‘science’ subsection featuring the science of CRISPR and xenotransplantation. Getting back to the Biennale and Piccinini: A major public art event since 1988, the Vancouver Biennale has hosted over 91 outdoor sculptures and new media works by more than 78 participating artists from over 25 countries and from 4 continents.

Quickie description of the 2018 – 2020 Vancouver Biennale

The latest edition of the Vancouver Biennale was featured in a June 6, 2018 news item on the Daily Hive (Vancouver),

The Vancouver Biennale will be bringing new —and unusual— works of public art to the city beginning this June.

The theme for this season’s Vancouver Biennale exhibition is “re-IMAGE-n” and it kicks off on June 20 [2018] in Vanier Park with Saudi artist Ajlan Gharem’s Paradise Has Many Gates.

Gharem’s architectural chain-link sculpture resembles a traditional mosque, the piece is meant to challenge the notions of religious orthodoxy and encourages individuals to image a space free of Islamophobia.

Melbourne artist Patricia Piccinini’s Curious Imaginings is expected to be one of the most talked about installations of the exhibit. Her style of “oddly captivating, somewhat grotesque, human-animal hybrid creature” is meant to be shocking and thought-provoking.

Piccinini’s interactive [emphasis mine] experience will “challenge us to explore the social impacts of emerging biotechnology and our ethical limits in an age where genetic engineering and digital technologies are already pushing the boundaries of humanity.”

Piccinini’s work will be displayed in the 105-year-old Patricia Hotel in Vancouver’s Strathcona neighbourhood. The 90-day ticketed exhibition [emphasis mine] is scheduled to open this September [2018].

Given that this blog is focused on nanotechnology and other emerging technologies such as CRISPR, I’m focusing on Piccinini’s work and its art/science or sci-art status. This image from the GOMA Gallery where Piccinini’s ‘Curious Affection‘ installation is being shown from March 24 – Aug. 5, 2018 in Brisbane, Queensland, Australia may give you some sense of what one of her installations is like,

Courtesy: Queensland Art Gallery | Gallery of Modern Art (QAGOMA)

I spoke with Serena at the Vancouver Biennale office and asked about the ‘interactive’ aspect of Piccinini’s installation. She suggested the term ‘immersive’ as an alternative. In other words, you won’t be playing with the sculptures or pressing buttons and interacting with computer screens or robots. She also noted that the ticket prices have not been set yet and they are currently developing events focused on the issues raised by the installation. She knew that 2018 is the 200th anniversary of the publication of Mary Shelley’s Frankenstein but I’m not sure how the Biennale folks plan (or don’t plan)  to integrate any recognition of the novle’s impact on the discussions about ‘new’ technologies .They expect Piccinini will visit Vancouver. (Note 1: Piccinini’s work can  also be seen in a group exhibition titled: Frankenstein’s Birthday Party at the Hosfselt Gallery in San Francisco (California, US) from June 23 – August 11, 2018.  Note 2: I featured a number of international events commemorating the 200th anniversary of the publication of Mary Shelley’s novel, Frankenstein, in my Feb. 26, 2018 posting. Note 3: The term ‘Frankenfoods’ helped to shape the discussion of genetically modified organisms and food supply on this planet. It was a wildly successful campaign for activists affecting legislation in some areas of research. Scientists have not been as enthusiastic about the effects. My January 15, 2009 posting briefly traces a history of the term.)

The 2018 – 2020 Vancouver Biennale and science

A June 7, 2018 Vancouver Biennale news release provides more detail about the current series of exhibitions,

The Biennale is also committed to presenting artwork at the cutting edge of discussion and in keeping with the STEAM (science, technology, engineering, arts, math[ematics]) approach to integrating the arts and sciences. In August [2018], Colombian/American visual artist Jessica Angel will present her monumental installation Dogethereum Bridge at Hinge Park in Olympic Village. Inspired by blockchain technology, the artwork’s design was created through the integration of scientific algorithms, new developments in technology, and the arts. This installation, which will serve as an immersive space and collaborative hub for artists and technologists, will host a series of activations with blockchain as the inspirational jumping-off point.

In what is expected to become one of North America’s most talked-about exhibitions of the year, Melbourne artist Patricia Piccinini’s Curious Imaginings will see the intersection of art, science, and ethics. For the first time in the Biennale’s fifteen years of creating transformative experiences, and in keeping with the 2018-2020 theme of “re-IMAGE-n,” the Biennale will explore art in unexpected places by exhibiting in unconventional interior spaces.  The hyperrealist “world of oddly captivating, somewhat grotesque, human-animal hybrid creatures” will be the artist’s first exhibit in a non-museum setting, transforming a wing of the 105-year-old Patricia Hotel. Situated in Vancouver’s oldest neighbourbood of Strathcona, Piccinini’s interactive experience will “challenge us to explore the social impacts of emerging bio-technology and our ethical limits in an age where genetic engineering and digital technologies are already pushing the boundaries of humanity.” In this intimate hotel setting located in a neighborhood continually undergoing its own change, Curious Imaginings will empower visitors to personally consider questions posed by the exhibition, including the promises and consequences of genetic research and human interference. …

There are other pieces being presented at the Biennale but my special interest is in the art/sci pieces and, at this point, CRISPR.

Piccinini in more depth

You can find out more about Patricia Piccinini in her biography on the Vancouver Biennale website but I found this Char Larsson April 7, 2018 article for the Independent (UK) more informative (Note: A link has been removed),

Patricia Piccinini’s sculptures are deeply disquieting. Walking through Curious Affection, her new solo exhibition at Brisbane’s Gallery of Modern Art, is akin to entering a science laboratory full of DNA experiments. Made from silicone, fibreglass and even human hair, her sculptures are breathtakingly lifelike, however, we can’t be sure what life they are like. The artist creates an exuberant parallel universe where transgenic experiments flourish and human evolution has given way to genetic engineering and DNA splicing.

Curious Affection is a timely and welcome recognition of Piccinini’s enormous contribution to reaching back to the mid-1990s. Working across a variety of mediums including photography, video and drawing, she is perhaps best known for her hyperreal creations.

As a genre, hyperrealism depends on the skill of the artist to create the illusion of reality. To be truly successful, it must convince the spectator of its realness. Piccinini acknowledges this demand, but with a delightful twist. The excruciating attention to detail deliberately solicits our desire to look, only to generate unease, as her sculptures are imbued with a fascinating otherness. Part human, part animal, the works are uncannily familiar, but also alarmingly “other”.

Inspired by advances in genetically modified pigs to generate replacement organs for humans [also known as xenotransplantation], we are reminded that Piccinini has always been at the forefront of debates concerning the possibilities of science, technology and DNA cloning. She does so, however, with a warm affection and sense of humour, eschewing the hysterical anxiety frequently accompanying these scientific developments.

Beyond the astonishing level of detail achieved by working with silicon and fibreglass, there is an ethics at work here. Piccinini is asking us not to avert our gaze from the other, and in doing so, to develop empathy and understanding through the encounter.

I encourage anyone who’s interested to read Larsson’s entire piece (April 7, 2018 article).

According to her Wikipedia entry, Piccinini works in a variety of media including video, sound, sculpture, and more. She also has her own website.

Gene editing and xenotransplantation

Sarah Zhang’s June 8, 2018 article for The Atlantic provides a peek at the extraordinary degree of interest and competition in the field of gene editing and CRISPR ((clustered regularly interspaced short palindromic repeats))/Cas9 research (Note: A link has been removed),

China Is Genetically Engineering Monkeys With Brain Disorders

Guoping Feng applied to college the first year that Chinese universities reopened after the Cultural Revolution. It was 1977, and more than a decade’s worth of students—5.7 million—sat for the entrance exams. Feng was the only one in his high school to get in. He was assigned—by chance, essentially—to medical school. Like most of his contemporaries with scientific ambitions, he soon set his sights on graduate studies in the United States. “China was really like 30 to 50 years behind,” he says. “There was no way to do cutting-edge research.” So in 1989, he left for Buffalo, New York, where for the first time he saw snow piled several feet high. He completed his Ph.D. in genetics at the State University of New York at Buffalo.

Feng is short and slim, with a monk-like placidity and a quick smile, and he now holds an endowed chair in neuroscience at MIT, where he focuses on the genetics of brain disorders. His 45-person lab is part of the McGovern Institute for Brain Research, which was established in 2000 with the promise of a $350 million donation, the largest ever received by the university. In short, his lab does not lack for much.

Yet Feng now travels to China several times a year, because there, he can pursue research he has not yet been able to carry out in the United States. [emphasis mine] …

Feng had organized a symposium at SIAT [Shenzhen Institutes of Advanced Technology], and he was not the only scientist who traveled all the way from the United States to attend: He invited several colleagues as symposium speakers, including a fellow MIT neuroscientist interested in tree shrews, a tiny mammal related to primates and native to southern China, and Chinese-born neuroscientists who study addiction at the University of Pittsburgh and SUNY Upstate Medical University. Like Feng, they had left China in the ’80s and ’90s, part of a wave of young scientists in search of better opportunities abroad. Also like Feng, they were back in China to pursue a type of cutting-edge research too expensive and too impractical—and maybe too ethically sensitive—in the United States.

Here’s what precipitated Feng’s work in China, (from Zhang’s article; Note: Links have been removed)

At MIT, Feng’s lab worked on genetically engineering a monkey species called marmosets, which are very small and genuinely bizarre-looking. They are cheaper to keep due to their size, but they are a relatively new lab animal, and they can be difficult to train on lab tasks. For this reason, Feng also wanted to study Shank3 on macaques in China. Scientists have been cataloging the social behavior of macaques for decades, making it an obvious model for studies of disorders like autism that have a strong social component. Macaques are also more closely related to humans than marmosets, making their brains a better stand-in for those of humans.

The process of genetically engineering a macaque is not trivial, even with the advanced tools of CRISPR. Researchers begin by dosing female monkeys with the same hormones used in human in vitro fertilization. They then collect and fertilize the eggs, and inject the resulting embryos with CRISPR proteins using a long, thin glass needle. Monkey embryos are far more sensitive than mice embryos, and can be affected by small changes in the pH of the injection or the concentration of CRISPR proteins. Only some of the embryos will have the desired mutation, and only some will survive once implanted in surrogate mothers. It takes dozens of eggs to get to just one live monkey, so making even a few knockout monkeys required the support of a large breeding colony.

The first Shank3 macaque was born in 2015. Four more soon followed, bringing the total to five.

To visit his research animals, Feng now has to fly 8,000 miles across 12 time zones. It would be a lot more convenient to carry out his macaque research in the United States, of course, but so far, he has not been able to.

He originally inquired about making Shank3 macaques at the New England Primate Research Center, one of eight national primate research centers then funded by the National Institutes of Health in partnership with a local institution (Harvard Medical School, in this case). The center was conveniently located in Southborough, Massachusetts, just 20 miles west of the MIT campus. But in 2013, Harvard decided to shutter the center.

The decision came as a shock to the research community, and it was widely interpreted as a sign of waning interest in primate research in the United States. While the national primate centers have been important hubs of research on HIV, Zika, Ebola, and other diseases, they have also come under intense public scrutiny. Animal-rights groups like the Humane Society of the United States have sent investigators to work undercover in the labs, and the media has reported on monkey deaths in grisly detail. Harvard officially made its decision to close for “financial” reasons. But the announcement also came after the high-profile deaths of four monkeys from improper handling between 2010 and 2012. The deaths sparked a backlash; demonstrators showed up at the gates. The university gave itself two years to wind down their primate work, officially closing the center in 2015.

“They screwed themselves,” Michael Halassa, the MIT neuroscientist who spoke at Feng’s symposium, told me in Shenzhen. Wei-Dong Yao, another one of the speakers, chimed in, noting that just two years later CRISPR has created a new wave of interest in primate research. Yao was one of the researchers at Harvard’s primate center before it closed; he now runs a lab at SUNY Upstate Medical University that uses genetically engineered mouse and human stem cells, and he had come to Shenzhen to talk about restarting his addiction research on primates.

Here’s comes the competition (from Zhang’s article; Note: Links have been removed),

While the U.S. government’s biomedical research budget has been largely flat, both national and local governments in China are eager to raise their international scientific profiles, and they are shoveling money into research. A long-rumored, government-sponsored China Brain Project is supposed to give neuroscience research, and primate models in particular, a big funding boost. Chinese scientists may command larger salaries, too: Thanks to funding from the Shenzhen local government, a new principal investigator returning from overseas can get 3 million yuan—almost half a million U.S. dollars—over his or her first five years. China is even finding success in attracting foreign researchers from top U.S. institutions like Yale.

In the past few years, China has seen a miniature explosion of genetic engineering in monkeys. In Kunming, Shanghai, and Guangzhou, scientists have created monkeys engineered to show signs of Parkinson’s, Duchenne muscular dystrophy, autism, and more. And Feng’s group is not even the only one in China to have created Shank3 monkeys. Another group—a collaboration primarily between researchers at Emory University and scientists in China—has done the same.

Chinese scientists’ enthusiasm for CRISPR also extends to studies of humans, which are moving much more quickly, and in some cases under less oversight, than in the West. The first studies to edit human embryos and first clinical trials for cancer therapies using CRISPR have all happened in China. [emphases mine]

Some ethical issues are also covered (from Zhang’s article),

Parents with severely epileptic children had asked him if it would be possible to study the condition in a monkey. Feng told them what he thought would be technically possible. “But I also said, ‘I’m not sure I want to generate a model like this,’” he recalled. Maybe if there were a drug to control the monkeys’ seizures, he said: “I cannot see them seizure all the time.”

But is it ethical, he continued, to let these babies die without doing anything? Is it ethical to generate thousands or millions of mutant mice for studies of brain disorders, even when you know they will not elucidate much about human conditions?

Primates should only be used if other models do not work, says Feng, and only if a clear path forward is identified. The first step in his work, he says, is to use the Shank3 monkeys to identify the changes the mutations cause in the brain. Then, researchers might use that information to find targets for drugs, which could be tested in the same monkeys. He’s talking with the Oregon National Primate Research Center about carrying out similar work in the United States. ….[Note: I have a three-part series about CRISPR and germline editing* in the US, precipitated by research coming out of Oregon, Part 1, which links to the other parts, is here.]

Zhang’s June 8, 2018 article is excellent and I highly recommend reading it.

I touched on the topic of xenotransplanttaion in a commentary on a book about the science  of the television series, Orphan Black in a January 31,2018 posting (Note: A chimera is what you use to incubate a ‘human’ organ for transplantation or, more accurately, xenotransplantation),

On the subject of chimeras, the Canadian Broadcasting Corporation (CBC) featured a January 26, 2017 article about the pig-human chimeras on its website along with a video,

The end

I am very excited to see Piccinini’s work come to Vancouver. There have been a number of wonderful art and art/science installations and discussions here but this is the first one (I believe) to tackle the emerging gene editing technologies and the issues they raise. (It also fits in rather nicely with the 200th anniversary of the publication of Mary Shelley’s Frankenstein which continues to raise issues and stimulate discussion.)

In addition to the ethical issues raised in Zhang’s article, there are some other philosophical questions:

  • what does it mean to be human
  • if we are going to edit genes to create hybrid human/animals, what are they and how do they fit into our current animal/human schema
  • are you still human if you’ve had an organ transplant where the organ was incubated in a pig

There are also going to be legal issues. In addition to any questions about legal status, there are also fights about intellectual property such as the one involving Harvard & MIT’s [Massachusetts Institute of Technology] Broad Institute vs the University of California at Berkeley (March 15, 2017 posting)..

While I’m thrilled about the Piccinini installation, it should be noted the issues raised by other artworks hosted in this version of the Biennale are important. Happily, they have been broached here in Vancouver before and I suspect this will result in more nuanced  ‘conversations’ than are possible when a ‘new’ issue is introduced.

Bravo 2018 – 2020 Vancouver Biennale!

* Germline editing is when your gene editing will affect subsequent generations as opposed to editing out a mutated gene for the lifetime of a single individual.

Art/sci and CRISPR links

This art/science posting may prove of some interest:

The connectedness of living things: an art/sci project in Saskatchewan: evolutionary biology (February 16, 2018)

A selection of my CRISPR posts:

CRISPR and editing the germline in the US (part 1 of 3): In the beginning (August 15, 2017)

NOTE: An introductory CRISPR video describing how CRISPR/Cas9 works was embedded in part1.

Why don’t you CRISPR yourself? (January 25, 2018)

Editing the genome with CRISPR ((clustered regularly interspaced short palindromic repeats)-carrying nanoparticles (January 26, 2018)

Immune to CRISPR? (April 10, 2018)

Machine learning software and quantum computers that think

A Sept. 14, 2017 news item on phys.org sets the stage for quantum machine learning by explaining a few basics first,

Language acquisition in young children is apparently connected with their ability to detect patterns. In their learning process, they search for patterns in the data set that help them identify and optimize grammar structures in order to properly acquire the language. Likewise, online translators use algorithms through machine learning techniques to optimize their translation engines to produce well-rounded and understandable outcomes. Even though many translations did not make much sense at all at the beginning, in these past years we have been able to see major improvements thanks to machine learning.

Machine learning techniques use mathematical algorithms and tools to search for patterns in data. These techniques have become powerful tools for many different applications, which can range from biomedical uses such as in cancer reconnaissance, in genetics and genomics, in autism monitoring and diagnosis and even plastic surgery, to pure applied physics, for studying the nature of materials, matter or even complex quantum systems.

Capable of adapting and changing when exposed to a new set of data, machine learning can identify patterns, often outperforming humans in accuracy. Although machine learning is a powerful tool, certain application domains remain out of reach due to complexity or other aspects that rule out the use of the predictions that learning algorithms provide.

Thus, in recent years, quantum machine learning has become a matter of interest because of is vast potential as a possible solution to these unresolvable challenges and quantum computers show to be the right tool for its solution.

A Sept. 14, 2017 Institute of Photonic Sciences ([Catalan] Institut de Ciències Fotòniques] ICFO) press release, which originated the news item, goes on to detail a recently published overview of the state of quantum machine learning,

In a recent study, published in Nature, an international team of researchers integrated by Jacob Biamonte from Skoltech/IQC, Peter Wittek from ICFO, Nicola Pancotti from MPQ, Patrick Rebentrost from MIT, Nathan Wiebe from Microsoft Research, and Seth Lloyd from MIT have reviewed the actual status of classical machine learning and quantum machine learning. In their review, they have thoroughly addressed different scenarios dealing with classical and quantum machine learning. In their study, they have considered different possible combinations: the conventional method of using classical machine learning to analyse classical data, using quantum machine learning to analyse both classical and quantum data, and finally, using classical machine learning to analyse quantum data.

Firstly, they set out to give an in-depth view of the status of current supervised and unsupervised learning protocols in classical machine learning by stating all applied methods. They introduce quantum machine learning and provide an extensive approach on how this technique could be used to analyse both classical and quantum data, emphasizing that quantum machines could accelerate processing timescales thanks to the use of quantum annealers and universal quantum computers. Quantum annealing technology has better scalability, but more limited use cases. For instance, the latest iteration of D-Wave’s [emphasis mine] superconducting chip integrates two thousand qubits, and it is used for solving certain hard optimization problems and for efficient sampling. On the other hand, universal (also called gate-based) quantum computers are harder to scale up, but they are able to perform arbitrary unitary operations on qubits by sequences of quantum logic gates. This resembles how digital computers can perform arbitrary logical operations on classical bits.

However, they address the fact that controlling a quantum system is very complex and analyzing classical data with quantum resources is not as straightforward as one may think, mainly due to the challenge of building quantum interface devices that allow classical information to be encoded into a quantum mechanical form. Difficulties, such as the “input” or “output” problems appear to be the major technical challenge that needs to be overcome.

The ultimate goal is to find the most optimized method that is able to read, comprehend and obtain the best outcomes of a data set, be it classical or quantum. Quantum machine learning is definitely aimed at revolutionizing the field of computer sciences, not only because it will be able to control quantum computers, speed up the information processing rates far beyond current classical velocities, but also because it is capable of carrying out innovative functions, such quantum deep learning, that could not only recognize counter-intuitive patterns in data, invisible to both classical machine learning and to the human eye, but also reproduce them.

As Peter Wittek [emphasis mine] finally states, “Writing this paper was quite a challenge: we had a committee of six co-authors with different ideas about what the field is, where it is now, and where it is going. We rewrote the paper from scratch three times. The final version could not have been completed without the dedication of our editor, to whom we are indebted.”

It was a bit of a surprise to see local (Vancouver, Canada) company D-Wave Systems mentioned but i notice that one of the paper’s authors (Peter Wittek) is mentioned in a May 22, 2017 D-Wave news release announcing a new partnership to foster quantum machine learning,

Today [May 22, 2017] D-Wave Systems Inc., the leader in quantum computing systems and software, announced a new initiative with the Creative Destruction Lab (CDL) at the University of Toronto’s Rotman School of Management. D-Wave will work with CDL, as a CDL Partner, to create a new track to foster startups focused on quantum machine learning. The new track will complement CDL’s successful existing track in machine learning. Applicants selected for the intensive one-year program will go through an introductory boot camp led by Dr. Peter Wittek [emphasis mine], author of Quantum Machine Learning: What Quantum Computing means to Data Mining, with instruction and technical support from D-Wave experts, access to a D-Wave 2000Q™ quantum computer, and the opportunity to use a D-Wave sampling service to enable machine learning computations and applications. D-Wave staff will be a part of the committee selecting up to 40 individuals for the program, which begins in September 2017.

For anyone interested in the paper, here’s a link to and a citation,

Quantum machine learning by Jacob Biamonte, Peter Wittek, Nicola Pancotti, Patrick Rebentrost, Nathan Wiebe, & Seth Lloyd. Nature 549, 195–202 (14 September 2017) doi:10.1038/nature23474 Published online 13 September 2017

This paper is behind a paywall.

Robot artists—should they get copyright protection

Clearly a lawyer wrote this June 26, 2017 essay on theconversation.com (Note: A link has been removed),

When a group of museums and researchers in the Netherlands unveiled a portrait entitled The Next Rembrandt, it was something of a tease to the art world. It wasn’t a long lost painting but a new artwork generated by a computer that had analysed thousands of works by the 17th-century Dutch artist Rembrandt Harmenszoon van Rijn.

The computer used something called machine learning [emphasis mine] to analyse and reproduce technical and aesthetic elements in Rembrandt’s works, including lighting, colour, brush-strokes and geometric patterns. The result is a portrait produced based on the styles and motifs found in Rembrandt’s art but produced by algorithms.

But who owns creative works generated by artificial intelligence? This isn’t just an academic question. AI is already being used to generate works in music, journalism and gaming, and these works could in theory be deemed free of copyright because they are not created by a human author.

This would mean they could be freely used and reused by anyone and that would be bad news for the companies selling them. Imagine you invest millions in a system that generates music for video games, only to find that music isn’t protected by law and can be used without payment by anyone in the world.

Unlike with earlier computer-generated works of art, machine learning software generates truly creative works without human input or intervention. AI is not just a tool. While humans program the algorithms, the decision making – the creative spark – comes almost entirely from the machine.

It could have been someone involved in the technology but nobody with that background would write “… something called machine learning … .”  Andres Guadamuz, lecturer in Intellectual Property Law at the University of Sussex, goes on to say (Note: Links have been removed),

Unlike with earlier computer-generated works of art, machine learning software generates truly creative works without human input or intervention. AI is not just a tool. While humans program the algorithms, the decision making – the creative spark – comes almost entirely from the machine.

That doesn’t mean that copyright should be awarded to the computer, however. Machines don’t (yet) have the rights and status of people under the law. But that doesn’t necessarily mean there shouldn’t be any copyright either. Not all copyright is owned by individuals, after all.

Companies are recognised as legal people and are often awarded copyright for works they don’t directly create. This occurs, for example, when a film studio hires a team to make a movie, or a website commissions a journalist to write an article. So it’s possible copyright could be awarded to the person (company or human) that has effectively commissioned the AI to produce work for it.

 

Things are likely to become yet more complex as AI tools are more commonly used by artists and as the machines get better at reproducing creativity, making it harder to discern if an artwork is made by a human or a computer. Monumental advances in computing and the sheer amount of computational power becoming available may well make the distinction moot. At that point, we will have to decide what type of protection, if any, we should give to emergent works created by intelligent algorithms with little or no human intervention.

The most sensible move seems to follow those countries that grant copyright to the person who made the AI’s operation possible, with the UK’s model looking like the most efficient. This will ensure companies keep investing in the technology, safe in the knowledge they will reap the benefits. What happens when we start seriously debating whether computers should be given the status and rights of people is a whole other story.

The team that developed a ‘new’ Rembrandt produced a video about the process,

Mark Brown’s April 5, 2016 article abut this project (which was unveiled on April 5, 2017 in Amsterdam, Netherlands) for the Guardian newspaper provides more detail such as this,

It [Next Rembrandt project] is the result of an 18-month project which asks whether new technology and data can bring back to life one of the greatest, most innovative painters of all time.

Advertising executive [Bas] Korsten, whose brainchild the project was, admitted that there were many doubters. “The idea was greeted with a lot of disbelief and scepticism,” he said. “Also coming up with the idea is one thing, bringing it to life is another.”

The project has involved data scientists, developers, engineers and art historians from organisations including Microsoft, Delft University of Technology, the Mauritshuis in The Hague and the Rembrandt House Museum in Amsterdam.

The final 3D printed painting consists of more than 148 million pixels and is based on 168,263 Rembrandt painting fragments.

Some of the challenges have been in designing a software system that could understand Rembrandt based on his use of geometry, composition and painting materials. A facial recognition algorithm was then used to identify and classify the most typical geometric patterns used to paint human features.

It sounds like it was a fascinating project but I don’t believe ‘The Next Rembrandt’ is an example of AI creativity or an example of the ‘creative spark’ Guadamuz discusses. This seems more like the kind of work  that could be done by a talented forger or fraudster. As I understand it, even when a human creates this type of artwork (a newly discovered and unknown xxx masterpiece), the piece is not considered a creative work in its own right. Some pieces are outright fraudulent and others which are described as “in the manner of xxx.”

Taking a somewhat different approach to mine, Timothy Geigner at Techdirt has also commented on the question of copyright and AI in relation to Guadamuz’s essay in a July 7, 2017 posting,

Unlike with earlier computer-generated works of art, machine learning software generates truly creative works without human input or intervention. AI is not just a tool. While humans program the algorithms, the decision making – the creative spark – comes almost entirely from the machine.

Let’s get the easy part out of the way: the culminating sentence in the quote above is not true. The creative spark is not the artistic output. Rather, the creative spark has always been known as the need to create in the first place. This isn’t a trivial quibble, either, as it factors into the simple but important reasoning for why AI and machines should certainly not receive copyright rights on their output.

That reasoning is the purpose of copyright law itself. Far too many see copyright as a reward system for those that create art rather than what it actually was meant to be: a boon to an artist to compensate for that artist to create more art for the benefit of the public as a whole. Artificial intelligence, however far progressed, desires only what it is programmed to desire. In whatever hierarchy of needs an AI might have, profit via copyright would factor either laughably low or not at all into its future actions. Future actions of the artist, conversely, are the only item on the agenda for copyright’s purpose. If receiving a copyright wouldn’t spur AI to create more art beneficial to the public, then copyright ought not to be granted.

Geigner goes on (July 7, 2017 posting) to elucidate other issues with the ideas expressed in the general debates of AI and ‘rights’ and the EU’s solution.

An explanation of neural networks from the Massachusetts Institute of Technology (MIT)

I always enjoy the MIT ‘explainers’ and have been a little sad that I haven’t stumbled across one in a while. Until now, that is. Here’s an April 14, 201 neural network ‘explainer’ (in its entirety) by Larry Hardesty (?),

In the past 10 years, the best-performing artificial-intelligence systems — such as the speech recognizers on smartphones or Google’s latest automatic translator — have resulted from a technique called “deep learning.”

Deep learning is in fact a new name for an approach to artificial intelligence called neural networks, which have been going in and out of fashion for more than 70 years. Neural networks were first proposed in 1944 by Warren McCullough and Walter Pitts, two University of Chicago researchers who moved to MIT in 1952 as founding members of what’s sometimes called the first cognitive science department.

Neural nets were a major area of research in both neuroscience and computer science until 1969, when, according to computer science lore, they were killed off by the MIT mathematicians Marvin Minsky and Seymour Papert, who a year later would become co-directors of the new MIT Artificial Intelligence Laboratory.

The technique then enjoyed a resurgence in the 1980s, fell into eclipse again in the first decade of the new century, and has returned like gangbusters in the second, fueled largely by the increased processing power of graphics chips.

“There’s this idea that ideas in science are a bit like epidemics of viruses,” says Tomaso Poggio, the Eugene McDermott Professor of Brain and Cognitive Sciences at MIT, an investigator at MIT’s McGovern Institute for Brain Research, and director of MIT’s Center for Brains, Minds, and Machines. “There are apparently five or six basic strains of flu viruses, and apparently each one comes back with a period of around 25 years. People get infected, and they develop an immune response, and so they don’t get infected for the next 25 years. And then there is a new generation that is ready to be infected by the same strain of virus. In science, people fall in love with an idea, get excited about it, hammer it to death, and then get immunized — they get tired of it. So ideas should have the same kind of periodicity!”

Weighty matters

Neural nets are a means of doing machine learning, in which a computer learns to perform some task by analyzing training examples. Usually, the examples have been hand-labeled in advance. An object recognition system, for instance, might be fed thousands of labeled images of cars, houses, coffee cups, and so on, and it would find visual patterns in the images that consistently correlate with particular labels.

Modeled loosely on the human brain, a neural net consists of thousands or even millions of simple processing nodes that are densely interconnected. Most of today’s neural nets are organized into layers of nodes, and they’re “feed-forward,” meaning that data moves through them in only one direction. An individual node might be connected to several nodes in the layer beneath it, from which it receives data, and several nodes in the layer above it, to which it sends data.

To each of its incoming connections, a node will assign a number known as a “weight.” When the network is active, the node receives a different data item — a different number — over each of its connections and multiplies it by the associated weight. It then adds the resulting products together, yielding a single number. If that number is below a threshold value, the node passes no data to the next layer. If the number exceeds the threshold value, the node “fires,” which in today’s neural nets generally means sending the number — the sum of the weighted inputs — along all its outgoing connections.

When a neural net is being trained, all of its weights and thresholds are initially set to random values. Training data is fed to the bottom layer — the input layer — and it passes through the succeeding layers, getting multiplied and added together in complex ways, until it finally arrives, radically transformed, at the output layer. During training, the weights and thresholds are continually adjusted until training data with the same labels consistently yield similar outputs.

Minds and machines

The neural nets described by McCullough and Pitts in 1944 had thresholds and weights, but they weren’t arranged into layers, and the researchers didn’t specify any training mechanism. What McCullough and Pitts showed was that a neural net could, in principle, compute any function that a digital computer could. The result was more neuroscience than computer science: The point was to suggest that the human brain could be thought of as a computing device.

Neural nets continue to be a valuable tool for neuroscientific research. For instance, particular network layouts or rules for adjusting weights and thresholds have reproduced observed features of human neuroanatomy and cognition, an indication that they capture something about how the brain processes information.

The first trainable neural network, the Perceptron, was demonstrated by the Cornell University psychologist Frank Rosenblatt in 1957. The Perceptron’s design was much like that of the modern neural net, except that it had only one layer with adjustable weights and thresholds, sandwiched between input and output layers.

Perceptrons were an active area of research in both psychology and the fledgling discipline of computer science until 1959, when Minsky and Papert published a book titled “Perceptrons,” which demonstrated that executing certain fairly common computations on Perceptrons would be impractically time consuming.

“Of course, all of these limitations kind of disappear if you take machinery that is a little more complicated — like, two layers,” Poggio says. But at the time, the book had a chilling effect on neural-net research.

“You have to put these things in historical context,” Poggio says. “They were arguing for programming — for languages like Lisp. Not many years before, people were still using analog computers. It was not clear at all at the time that programming was the way to go. I think they went a little bit overboard, but as usual, it’s not black and white. If you think of this as this competition between analog computing and digital computing, they fought for what at the time was the right thing.”

Periodicity

By the 1980s, however, researchers had developed algorithms for modifying neural nets’ weights and thresholds that were efficient enough for networks with more than one layer, removing many of the limitations identified by Minsky and Papert. The field enjoyed a renaissance.

But intellectually, there’s something unsatisfying about neural nets. Enough training may revise a network’s settings to the point that it can usefully classify data, but what do those settings mean? What image features is an object recognizer looking at, and how does it piece them together into the distinctive visual signatures of cars, houses, and coffee cups? Looking at the weights of individual connections won’t answer that question.

In recent years, computer scientists have begun to come up with ingenious methods for deducing the analytic strategies adopted by neural nets. But in the 1980s, the networks’ strategies were indecipherable. So around the turn of the century, neural networks were supplanted by support vector machines, an alternative approach to machine learning that’s based on some very clean and elegant mathematics.

The recent resurgence in neural networks — the deep-learning revolution — comes courtesy of the computer-game industry. The complex imagery and rapid pace of today’s video games require hardware that can keep up, and the result has been the graphics processing unit (GPU), which packs thousands of relatively simple processing cores on a single chip. It didn’t take long for researchers to realize that the architecture of a GPU is remarkably like that of a neural net.

Modern GPUs enabled the one-layer networks of the 1960s and the two- to three-layer networks of the 1980s to blossom into the 10-, 15-, even 50-layer networks of today. That’s what the “deep” in “deep learning” refers to — the depth of the network’s layers. And currently, deep learning is responsible for the best-performing systems in almost every area of artificial-intelligence research.

Under the hood

The networks’ opacity is still unsettling to theorists, but there’s headway on that front, too. In addition to directing the Center for Brains, Minds, and Machines (CBMM), Poggio leads the center’s research program in Theoretical Frameworks for Intelligence. Recently, Poggio and his CBMM colleagues have released a three-part theoretical study of neural networks.

The first part, which was published last month in the International Journal of Automation and Computing, addresses the range of computations that deep-learning networks can execute and when deep networks offer advantages over shallower ones. Parts two and three, which have been released as CBMM technical reports, address the problems of global optimization, or guaranteeing that a network has found the settings that best accord with its training data, and overfitting, or cases in which the network becomes so attuned to the specifics of its training data that it fails to generalize to other instances of the same categories.

There are still plenty of theoretical questions to be answered, but CBMM researchers’ work could help ensure that neural networks finally break the generational cycle that has brought them in and out of favor for seven decades.

This image from MIT illustrates a ‘modern’ neural network,

Most applications of deep learning use “convolutional” neural networks, in which the nodes of each layer are clustered, the clusters overlap, and each cluster feeds data to multiple nodes (orange and green) of the next layer. Image: Jose-Luis Olivares/MIT

h/t phys.org April 17, 2017

One final note, I wish the folks at MIT had an ‘explainer’ archive. I’m not sure how to find any more ‘explainers on MIT’s website.