Monthly Archives: January 2024

A hardware (neuromorphic and quantum) proposal for handling increased AI workload

Leave a reply

It’s been a while since I’ve featured anything from Purdue University (Indiana, US). From a November 7, 2023 news item on Nanowerk, Note Links have been removed,

Technology is edging closer and closer to the super-speed world of computing with artificial intelligence. But is the world equipped with the proper hardware to be able to handle the workload of new AI technological breakthroughs?

Key Takeaways
Current AI technologies are strained by the limitations of silicon-based computing hardware, necessitating new solutions.

Research led by Erica Carlson [Purdue University] suggests that neuromorphic [brainlike] architectures, which replicate the brain’s neurons and synapses, could revolutionize computing efficiency and power.

Vanadium oxides have been identified as a promising material for creating artificial neurons and synapses, crucial for neuromorphic computing.

Innovative non-volatile memory, observed in vanadium oxides, could be the key to more energy-efficient and capable AI hardware.

Future research will explore how to optimize the synaptic behavior of neuromorphic materials by controlling their memory properties.

…

The colored landscape above shows a transition temperature map of VO2 (pink surface) as measured by optical microscopy. This reveals the unique way that this neuromorphic quantum material [emphasis mine] stores memory like a synapse. Image credit: Erica Carlson, Alexandre Zimmers, and Adobe Stock

An October 13, 2023 Purdue University news release (also on EurekAlert but published November 6, 2023) by Cheryl Pierce, which originated the news item, provides more detail about the work, Note: A link has been removed,

“The brain-inspired codes of the AI revolution are largely being run on conventional silicon computer architectures which were not designed for it,” explains Erica Carlson, 150th Anniversary Professor of Physics and Astronomy at Purdue University.

A joint effort between Physicists from Purdue University, University of California San Diego (USCD) and École Supérieure de Physique et de Chimie Industrielles (ESPCI) in Paris, France, believe they may have discovered a way to rework the hardware…. [sic] By mimicking the synapses of the human brain.  They published their findings, “Spatially Distributed Ramp Reversal Memory in VO2” in Advanced Electronic Materials which is featured on the back cover of the October 2023 edition.

New paradigms in hardware will be necessary to handle the complexity of tomorrow’s computational advances. According to Carlson, lead theoretical scientist of this research, “neuromorphic architectures hold promise for lower energy consumption processors, enhanced computation, fundamentally different computational modes, native learning and enhanced pattern recognition.”

Neuromorphic architecture basically boils down to computer chips mimicking brain behavior.  Neurons are cells in the brain that transmit information. Neurons have small gaps at their ends that allow signals to pass from one neuron to the next which are called synapses. In biological brains, these synapses encode memory. This team of scientists concludes that vanadium oxides show tremendous promise for neuromorphic computing because they can be used to make both artificial neurons and synapses.

“The dissonance between hardware and software is the origin of the enormously high energy cost of training, for example, large language models like ChatGPT,” explains Carlson. “By contrast, neuromorphic architectures hold promise for lower energy consumption by mimicking the basic components of a brain: neurons and synapses. Whereas silicon is good at memory storage, the material does not easily lend itself to neuron-like behavior. Ultimately, to provide efficient, feasible neuromorphic hardware solutions requires research into materials with radically different behavior from silicon – ones that can naturally mimic synapses and neurons. Unfortunately, the competing design needs of artificial synapses and neurons mean that most materials that make good synaptors fail as neuristors, and vice versa. Only a handful of materials, most of them quantum materials, have the demonstrated ability to do both.”

The team relied on a recently discovered type of non-volatile memory which is driven by repeated partial temperature cycling through the insulator-to-metal transition. This memory was discovered in vanadium oxides.

Alexandre Zimmers, lead experimental scientist from Sorbonne University and École Supérieure de Physique et de Chimie Industrielles, Paris, explains, “Only a few quantum materials are good candidates for future neuromorphic devices, i.e., mimicking artificial synapses and neurons. For the first time, in one of them, vanadium dioxide, we can see optically what is changing in the material as it operates as an artificial synapse. We find that memory accumulates throughout the entirety of the sample, opening new opportunities on how and where to control this property.”

“The microscopic videos show that, surprisingly, the repeated advance and retreat of metal and insulator domains causes memory to be accumulated throughout the entirety of the sample, rather than only at the boundaries of domains,” explains Carlson. “The memory appears as shifts in the local temperature at which the material transitions from insulator to metal upon heating, or from metal to insulator upon cooling. We propose that these changes in the local transition temperature accumulate due to the preferential diffusion of point defects into the metallic domains that are interwoven through the insulator as the material is cycled partway through the transition.”

Now that the team has established that vanadium oxides are possible candidates for future neuromorphic devices, they plan to move forward in the next phase of their research.

“Now that we have established a way to see inside this neuromorphic material, we can locally tweak and observe the effects of, for example, ion bombardment on the material’s surface,” explains Zimmers. “This could allow us to guide the electrical current through specific regions in the sample where the memory effect is at its maximum. This has the potential to significantly enhance the synaptic behavior of this neuromorphic material.”

There’s a very interesting 16 mins. 52 secs. video embedded in the October 13, 2023 Purdue University news release. In an interview with Dr. Erica Carlson who hosts The Quantum Age website and video interviews on its YouTube Channel, Alexandre Zimmers takes you from an amusing phenomenon observed by 19th century scientists through the 20th century where it becomes of more interest as the nanscale phenonenon can be exploited (sonar, scanning tunneling microscopes, singing birthday cards, etc.) to the 21st century where we are integrating this new information into a quantum* material for neuromorphic hardware.

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

Spatially Distributed Ramp Reversal Memory in VO2 by Sayan Basak, Yuxin Sun, Melissa Alzate Banguero, Pavel Salev, Ivan K. Schuller, Lionel Aigouy, Erica W. Carlson, Alexandre Zimmers. Advanced Electronic Materials Volume 9, Issue 10 October 2023 2300085 DOI: https://doi.org/10.1002/aelm.202300085 First published: 10 July 2023

This paper is open access.

There’s a lot of research into neuromorphic hardware, here’s a sampling of some of my most recent posts on the topic,

There’s more, just use ‘neuromorphic hardware’ for your search term.

*’meta’ changed to ‘quantum’ on January 8, 2024.

XoMotion, an exoskeleton developed in Canada causes commotion

Leave a reply

I first stumbled across these researchers in 2016 when their project was known as “Wearable Lower Limb Anthropomorphic Exoskeleton (WLLAE).” In my January 20, 2016 posting, “#BCTECH: being at the Summit (Jan. 18-19, 2016),” an event put on by the province of British Columbia (BC, Canada) and the BC Innovation Council (BCIC), I visited a number of booths and talks at the #BC TECH Summit and had this to say about WLLAE,

“The Wearable Lower Limb Anthropomorphic Exoskeleton (WLLAE) – a lightweight, battery-operated and ergonomic robotic system to help those with mobility issues improve their lives. The exoskeleton features joints and links that correspond to those of a human body and sync with motion. SFU has designed, manufactured and tested a proof-of-concept prototype and the current version can mimic all the motions of hip joints.” The researchers (Siamak Arzanpour and Edward Park) pointed out that the ability to mimic all the motions of the hip is a big difference between their system and others which only allow the leg to move forward or back. They rushed the last couple of months to get this system ready for the Summit. In fact, they received their patent for the system the night before (Jan. 17, 2016) the Summit opened.

…

Unfortunately, there aren’t any pictures of WLLAE yet and the proof-of-concept version may differ significantly from the final version. This system could be used to help people regain movement (paralysis/frail seniors) and I believe there’s a possibility it could be used to enhance human performance (soldiers/athletes). The researchers still have some significant hoops to jump before getting to the human clinical trial stage. They need to refine their apparatus, ensure that it can be safely operated, and further develop the interface between human and machine. I believe WLLAE is considered a neuroprosthetic device. While it’s not a fake leg or arm, it enables movement (prosthetic) and it operates on brain waves (neuro). It’s a very exciting area of research, consequently, there’s a lot of international competition. [ETA January 3, 2024: I’m pretty sure I got the neuroprosthetic part wrong]

Time moved on and there was a name change and then there was this November 10, 2023 article by Jeremy Hainsworth for the Vancouver is Awesome website,

Vancouver-based fashion designer Chloe Angus thought she’d be in a wheelchair for the rest of her life after being diagnosed with an inoperable benign tumour in her spinal cord in 2015, resulting in permanent loss of mobility in her legs.

Now, however, she’s been using a state-of-the-art robotic exoskeleton known as XoMotion that can help physically disabled people self-balance, walk, sidestep, climb stairs and crouch.

“The first time I walked with the exoskeleton was a jaw-dropping experience,” said Angus. “After all these years, the exoskeleton let me stand up and walk on my own without falling. I felt like myself again.”

She added the exoskeleton has the potential to completely change the world for people with motion disabilities.

XoMotion is the result of a decade of research and the product of a Simon Fraser University spinoff company, Human in Motion Robotics (HMR) Inc. It’s the brainchild of professors Siamak Arzanpour and Edward Park.

Arzanpour and Park, both researchers in the Burnaby-based university’s School of Mechatronic Systems Engineering, began work on the device in 2014. They had a vision to enhance exoskeleton technology and empower individuals with mobility challenges to have more options for movement.

“We felt that there was an immediate need to help people with motion disabilities to walk again, with a full range of motion. At the time, exoskeletons could only walk forward. That was the only motion possible,” Arzanpour said.

…

A November 15, 2023 article (with an embedded video) by Amy Judd & Alissa Thibault for Global News (television) highlights Alexander’s story,

…

SFU professors Siamak Arzanpour and Edward Park wanted to help people with motion disabilities to walk freely, naturally and independently.

The exoskeleton [XoMotion] is now the most advanced of its kind in the world.

Chloe Angus, who lost her mobility in her legs in 2015, now works for the team.

She said the exoskeleton makes her feel like herself again.

…

She was diagnosed with an inoperable benign tumor in her spinal cord in 2015 which resulted in a sudden and permanent loss of mobility in her legs. At the time, doctors told Angus that she would need a wheelchair to move for the rest of her life.

Now she is part of the project and defying all odds.

“After all these years, the exoskeleton let me stand up and walk on my own without falling. I felt like myself again.”

…

There’s a bit more information in the November 8, 2023 Simon Fraser University (SFU) news release (which has the same embedded video as the Global News article) by Ray Sharma,

The state-of-the-art robotic exoskeleton known as XoMotion is the result of a decade of research and the product of an SFU spin off company, Human in Motion Robotics (HMR) Inc. The company has recently garnered millions in investment, an overseas partnership and a suite of new offices in Vancouver.

XoMotion allows individuals with mobility challenges to stand up and walk on their own, without additional support. When in use, XoMotion maintains its stability and simultaneously encompasses all the ranges of motion and degrees of freedom needed for users to self-balance, walk, sidestep, climb stairs, crouch, and more. 

Sensors within the lower-limb exoskeleton mimic the human body’s sense of logic to identify structures along the path, and in-turn, generate a fully balanced motion.

SFU professors Siamak Arzanpour and Edward Park, both researchers in the School of Mechatronic Systems Engineering, began work on the device in 2014 with a vision to enhance exoskeleton technology and empower individuals with mobility challenges to have more options for movement. 

“We felt that there was an immediate need to help people with motion disabilities to walk again, with a full range of motion. At the time, exoskeletons could only walk forward. That was the only motion possible,” says Arzanpour. 

The SFU professors, who first met in 2001 as graduate students at the University of Toronto, co-founded HMR in 2016, bringing together a group of students, end-users, therapists, and organizations to build upon the exoskeleton. Currently, 70 per cent of HMR employees are SFU graduates. 

…

In recent years, HMR has garnered multiple streams of investment, including a contract with Innovative Solutions Canada, and $10 million in funding during their Series A round in May, including an $8 million investment and strategic partnership from Beno TNR, a prominent Korean technology investment firm.

…

I decided to bring the embedded video here, it runs a little over 2 mins.,

You can find the Human in Robotics (HMR) website here.

Economic impacts (2002 – 2022) and the US National Nanotechnology Initiative (NNI)

Leave a reply

Lynn L. Bergeron’s and Carla Hutton’s December 27, 2023 posting on The National Law Review announced a new report from the US National Nanotechnology Initiative (NNI), Note: A link has been removed,

On December 5, 2023, the National Nanotechnology Initiative (NNI) released a report analyzing the economic impact of federal investment in nanotechnology from 2002 to 2022 [emphasis mine]. The report states that NNI selected this timeframe because it was codified by the 21st Century Nanotechnology Research and Development Act in 2003, and thus the range covers its entire existence. The report examines the impact of public investment, growth and trends of the market, and the evolving understanding and application of nanotechnology in the United States. It also provides key data for evaluating NNI’s ability to fulfill its mission and illustrates NNI’s successes to date.

NNI notes that in 2022, the U.S. Census Bureau released data from its 2017 Economic Census, and data in the classification code of Nanotechnology Research and Development (R&D) revealed that more than 3,700 companies, employing more than 171,000 people, reported $42 billion in annual revenue and $20 billion in employee salaries. According to NNI, these numbers “suffered from a limited scope, as the Bureau only included companies that self-identified as primarily being in the business of nanotechnology R&D.” To understand better the complete picture, NNI commissioned the Parnin Group to conduct a more complete economic impact analysis. [all emphases mine]

…

You can find the more conservative claim of a $42 billion impact on the US economy in this November 28, 2022 NNI post by Mike Kiley. This year’s December 5, 2023 NNI post by Mike Kiley updates the numbers based on a new report,

An independent study focusing on the aggregated revenues of a select list of nanotechnology companies has estimated that the 2022 economic impact of nanotechnology on the U.S. economy was between $67 billion and $83 billion and close to a trillion dollars over the past two decades . This dwarfs the U.S. Government’s investment of around $40 billion over that same timeframe, which corresponds to the nation’s prioritization of the field through the National Nanotechnology Initiative (NNI).

The NNI investment has been used to explore the potential of nanoscale science, to capture societal benefits of nanotechnology, and to establish and sustain U.S. leadership in this critical field, both scientifically and economically. While it is difficult to fully capture the economic impact of the NNI’s sustained focus, these numbers hint at the tremendous multiplier effect that nanotechnology investments have had on the economy and the Nation.

As impressive as these numbers are, they only represent a relatively small number of companies that are clearly classified as nanotechnology. This limited approach ignores the field’s critical supporting role in several large commercial sectors. Therefore, the study also explored the impact of one closely related industry – microelectronics and semiconductors – to provide anecdotal evidence of the full magnitude of nanotechnology on the nation’s economy.

Examining the impact of the addition of the microelectronics and semiconductor industry to the study resulted in an estimate of $268 – 297 billion in 2022 alone. While significantly higher than the initial analysis, the authors recognized that this estimate still does not capture the full scope of the nano-economy, since microelectronics and semiconductors are only one of many commercial areas that substantially benefited from the nation’s leadership in the field.

Zooming in on the Not-So-Nano Numbers

In late 2022, the U.S. Census Bureau released data from its 2017 Economic Census. In the classification code of Nanotechnology Research and Development (R&D), the data revealed that over 3,700 companies, employing more than 171,000 people, reported $42 billion in annual revenue and $20 billion in employee salaries. As noted in a previous NNCO blog post , released on Nov. 28, 2022, these numbers also suffered from a limited scope, as the Bureau only included companies that self-identified as primarily being in the business of nanotechnology R&D. This limited scope led to a desire to better understand the full picture.

In early 2023, the NNI commissioned the Parnin Group (Alexandria, VA) to conduct a more complete economic impact analysis of nanotechnology to the U.S. economy . To conduct this analysis, the report identified a variety of nanotechnology products, including nanomaterials, intermediate nanotechnology products, and finished products in the marketplace. These products were organized into four categories: (1) core nano (e.g., carbon nanotubes), (2) nano tools (e.g., nanoscale etching tools), (3) integrated nano (e.g., mRNA vaccines), and (4) nano-enabled (e.g., pharmaceuticals). Once products and their parent companies were identified, Parnin examined Bureau of Labor Statistics data, value-chain analysis, product categories, public companies’ Securities and Exchange Commission filings, and patent filings to establish the collective economic value produced by these companies.

Clearly, capturing the economic impact of nanotechnology is not trivial. Products used every day are enabled by nanotechnology, but “nanotechnology” is not seen in the packaging of some of the most ubiquitous items in our lives, like a smartphone, e-reader, or television. Companies and products seldom draw attention to nanomaterials used to make them, for various reasons, including protecting proprietary formulations and practices. As a result, many large companies and related commercial areas – including microelectronics and semiconductors, healthcare, pharmaceutical production, oil and gas refining, and cosmetic products – that have operations and products in the nanotechnology space, but not exclusively so, were excluded from this economic analysis, leading to conservative estimates of the economic impact of nanotechnology.

The report explored the omission of these major areas through an analysis of nanotechnology’s contribution in one of these sectors: microelectronics and semiconductors. While it represents one of the clearest examples of how nanotechnology is used to drive the U.S. economy, the microelectronics industry was mostly excluded in the initial analysis since, historically, it has been unclear what percentage of companies’ portfolios were related to nanotechnology. However, by 2022 every competitive product in the sector features nanoscale dimensions created through nanotechnology tools, creating confidence that this area can defensibly be included in an analysis of the nano-economy.

As indicated earlier, when the microelectronics and semiconductor segments were included, the estimated impact jumped to between $268 billion and $297 billion annually. While other sectors are not as clearly connected to the field of nanotechnology, they are a part of the story and this exploration provides a glimpse into how sizeable the field’s impact might be.

Caveats and nuances abound, because seeing the impact of nanotechnology to the U.S. economy would be like seeing a 10-nanometer object in the palm of your hand; it is there, but you need special tools to see it! And regardless of the exact number, the message is clear: The United States’ leadership in the field has certainly paid off.

Report: Assessing the Economic Impact of Nanotechnology in the United States

The report (title page: Economic Impact Analysis: 20 Years of Nanotechnology Investments) covering 2002-2022 is relatively short, 56 pp. in the print version or 57 pp. in the PDF.

Eye-opening to me, was that the NNI never included semi-conductors and micro-elecronics in its previous economic analyses. Pretty significant omission.

I have no background in economics and so, much of the report flew over my head. However, I am a long time (and experienced skeptic) and can’t help suspecting that everyone (especially the client, in this case, the US government) is much happier with these new numbers. Lest we forget, the NNI was signed into existence by a Democratic president, Bill Clinton and the administration is now led by another Democratic president, Joe Biden. As well, this report was released just in time for 2024, an election year.

While I think there might have been a little over enthusiasm in the estimates, the report seems to bear out the notion that nanotechnology is increasingly a foundational element of modern technology and products.