Tag Archives: nanochips

Electronics begone! Enter: the light-based brainlike computing chip

Leave a reply

At this point, it’s possible I’m wrong but I think this is the first ‘memristor’ type device (also called a neuromorphic chip) based on light rather than electronics that I’ve featured here on this blog. In other words, it’s not, technically speaking, a memristor but it does have the same properties so it is a neuromorphic chip.

Caption: The optical microchips that the researchers are working on developing are about the size of a one-cent piece. Credit: WWU Muenster – Peter Leßmann

A May 8, 2019 news item on Nanowerk announces this new approach to neuromorphic hardware (Note: A link has been removed),

Researchers from the Universities of Münster (Germany), Oxford and Exeter (both UK) have succeeded in developing a piece of hardware which could pave the way for creating computers which resemble the human brain.

The scientists produced a chip containing a network of artificial neurons that works with light and can imitate the behaviour of neurons and their synapses. The network is able to “learn” information and use this as a basis for computing and recognizing patterns. As the system functions solely with light and not with electrons, it can process data many times faster than traditional systems. …

A May 8, 2019 University of Münster press release (also on EurekAlert), which originated the news item, reveals the full story,

A technology that functions like a brain? In these times of artificial intelligence, this no longer seems so far-fetched – for example, when a mobile phone can recognise faces or languages. With more complex applications, however, computers still quickly come up against their own limitations. One of the reasons for this is that a computer traditionally has separate memory and processor units – the consequence of which is that all data have to be sent back and forth between the two. In this respect, the human brain is way ahead of even the most modern computers because it processes and stores information in the same place – in the synapses, or connections between neurons, of which there are a million-billion in the brain. An international team of researchers from the Universities of Münster (Germany), Oxford and Exeter (both UK) have now succeeded in developing a piece of hardware which could pave the way for creating computers which resemble the human brain. The scientists managed to produce a chip containing a network of artificial neurons that works with light and can imitate the behaviour of neurons and their synapses.

The researchers were able to demonstrate, that such an optical neurosynaptic network is able to “learn” information and use this as a basis for computing and recognizing patterns – just as a brain can. As the system functions solely with light and not with traditional electrons, it can process data many times faster. “This integrated photonic system is an experimental milestone,” says Prof. Wolfram Pernice from Münster University and lead partner in the study. “The approach could be used later in many different fields for evaluating patterns in large quantities of data, for example in medical diagnoses.” The study is published in the latest issue of the “Nature” journal.

The story in detail – background and method used

Most of the existing approaches relating to so-called neuromorphic networks are based on electronics, whereas optical systems – in which photons, i.e. light particles, are used – are still in their infancy. The principle which the German and British scientists have now presented works as follows: optical waveguides that can transmit light and can be fabricated into optical microchips are integrated with so-called phase-change materials – which are already found today on storage media such as re-writable DVDs. These phase-change materials are characterised by the fact that they change their optical properties dramatically, depending on whether they are crystalline – when their atoms arrange themselves in a regular fashion – or amorphous – when their atoms organise themselves in an irregular fashion. This phase-change can be triggered by light if a laser heats the material up. “Because the material reacts so strongly, and changes its properties dramatically, it is highly suitable for imitating synapses and the transfer of impulses between two neurons,” says lead author Johannes Feldmann, who carried out many of the experiments as part of his PhD thesis at the Münster University.

In their study, the scientists succeeded for the first time in merging many nanostructured phase-change materials into one neurosynaptic network. The researchers developed a chip with four artificial neurons and a total of 60 synapses. The structure of the chip – consisting of different layers – was based on the so-called wavelength division multiplex technology, which is a process in which light is transmitted on different channels within the optical nanocircuit.

In order to test the extent to which the system is able to recognise patterns, the researchers “fed” it with information in the form of light pulses, using two different algorithms of machine learning. In this process, an artificial system “learns” from examples and can, ultimately, generalise them. In the case of the two algorithms used – both in so-called supervised and in unsupervised learning – the artificial network was ultimately able, on the basis of given light patterns, to recognise a pattern being sought – one of which was four consecutive letters.

“Our system has enabled us to take an important step towards creating computer hardware which behaves similarly to neurons and synapses in the brain and which is also able to work on real-world tasks,” says Wolfram Pernice. “By working with photons instead of electrons we can exploit to the full the known potential of optical technologies – not only in order to transfer data, as has been the case so far, but also in order to process and store them in one place,” adds co-author Prof. Harish Bhaskaran from the University of Oxford.

A very specific example is that with the aid of such hardware cancer cells could be identified automatically. Further work will need to be done, however, before such applications become reality. The researchers need to increase the number of artificial neurons and synapses and increase the depth of neural networks. This can be done, for example, with optical chips manufactured using silicon technology. “This step is to be taken in the EU joint project ‘Fun-COMP’ by using foundry processing for the production of nanochips,” says co-author and leader of the Fun-COMP project, Prof. C. David Wright from the University of Exeter.

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

All-optical spiking neurosynaptic networks with self-learning capabilities by J. Feldmann, N. Youngblood, C. D. Wright, H. Bhaskaran & W. H. P. Pernice. Nature volume 569, pages208–214 (2019) DOI: https://doi.org/10.1038/s41586-019-1157-8 Issue Date: 09 May 2019

This paper is behind a paywall.

For the curious, I found a little more information about Fun-COMP (functionally-scaled computer technology). It’s a European Commission (EC) Horizon 2020 project coordinated through the University of Exeter. For information with details such as the total cost, contribution from the EC, the list of partnerships and more there is the Fun-COMP webpage on fabiodisconzi.com.

Making nanoscale transistor chips out of thin air—sort of

Leave a reply

Caption: The nano-gap transistors operating in air. As gaps become smaller than the mean-free path of electrons in air, there is ballistic electron transport. Credit: RMIT University

A November 19, 2018 news item on Nanowerk describes the ‘airy’ work ( Note: A link has been removed),

Researchers at RMIT University [Ausralia] have engineered a new type of transistor, the building block for all electronics. Instead of sending electrical currents through silicon, these transistors send electrons through narrow air gaps, where they can travel unimpeded as if in space.

The device unveiled in material sciences journal Nano Letters (“Metal–Air Transistors: Semiconductor-free field-emission air-channel nanoelectronics”), eliminates the use of any semiconductor at all, making it faster and less prone to heating up.

A November 19, 2018 RMIT University news release on EurkeAlert, which originated the news item, describes the work and possibilities in more detail,

Lead author and PhD candidate in RMIT’s Functional Materials and Microsystems Research Group, Ms Shruti Nirantar, said this promising proof-of-concept design for nanochips as a combination of metal and air gaps could revolutionise electronics.

“Every computer and phone has millions to billions of electronic transistors made from silicon, but this technology is reaching its physical limits where the silicon atoms get in the way of the current flow, limiting speed and causing heat,” Nirantar said.

“Our air channel transistor technology has the current flowing through air, so there are no collisions to slow it down and no resistance in the material to produce heat.”

The power of computer chips – or number of transistors squeezed onto a silicon chip – has increased on a predictable path for decades, roughly doubling every two years. But this rate of progress, known as Moore’s Law, has slowed in recent years as engineers struggle to make transistor parts, which are already smaller than the tiniest viruses, smaller still.

Nirantar says their research is a promising way forward for nano electronics in response to the limitation of silicon-based electronics.

“This technology simply takes a different pathway to the miniaturisation of a transistor in an effort to uphold Moore’s Law for several more decades,” Shruti said.

Research team leader Associate Professor Sharath Sriram said the design solved a major flaw in traditional solid channel transistors – they are packed with atoms – which meant electrons passing through them collided, slowed down and wasted energy as heat.

“Imagine walking on a densely crowded street in an effort to get from point A to B. The crowd slows your progress and drains your energy,” Sriram said.

“Travelling in a vacuum on the other hand is like an empty highway where you can drive faster with higher energy efficiency.”

But while this concept is obvious, vacuum packaging solutions around transistors to make them faster would also make them much bigger, so are not viable.

“We address this by creating a nanoscale gap between two metal points. The gap is only a few tens of nanometers, or 50,000 times smaller than the width of a human hair, but it’s enough to fool electrons into thinking that they are travelling through a vacuum and re-create a virtual outer-space for electrons within the nanoscale air gap,” he said.

The nanoscale device is designed to be compatible with modern industry fabrication and development processes. It also has applications in space – both as electronics resistant to radiation and to use electron emission for steering and positioning ‘nano-satellites’.

“This is a step towards an exciting technology which aims to create something out of nothing to significantly increase speed of electronics and maintain pace of rapid technological progress,” Sriram said.

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

Metal–Air Transistors: Semiconductor-free field-emission air-channel nanoelectronics by
Shruti Nirantar, Taimur Ahmed, Guanghui Ren, Philipp Gutruf, Chenglong Xu, Madhu Bhaskaran, Sumeet Walia, and Sharath Sriram. Nano Lett., DOI: 10.1021/acs.nanolett.8b02849 Publication Date (Web): November 16, 2018

Copyright © 2018 American Chemical Society

This paper is behind a paywall.