A wafer filled with memristors
Courtesy of UCL
Extremely energy-efficient artificial intelligence is now closer to reality after a study by UCL researchers found a way to improve the accuracy of a brain-inspired computing system
The system, which uses memristors to create artificial neural networks, is at least 1,000 times more energy efficient than conventional transistor-based AI hardware, but has until now been more prone to error.
Existing AI is extremely energy-intensive – training one AI model can generate 284 tonnes of carbon dioxide, equivalent to the lifetime emissions of five cars. Replacing the transistors that make up all digital devices with memristors, a novel electronic device first built in 2008, could reduce this to a fraction of a tonne of carbon dioxide – equivalent to emissions generated in an afternoon’s drive.
Since memristors are so much more energy-efficient than existing computing systems, they can potentially pack huge amounts of computing power into hand-held devices, removing the need to be connected to the Internet.
This is especially important as over-reliance on the Internet is expected to become problematic in future due to ever-increasing data demands and the difficulties of increasing data transmission capacity past a certain point.
In the new study, published in Nature Communications, engineers at UCL found that accuracy could be greatly improved by getting memristors to work together in several sub-groups of neural networks and averaging their calculations, meaning that flaws in each of the networks could be cancelled out.
Memristors, described as “resistors with memory”, as they remember the amount of electric charge that flowed through them even after being turned off, were considered revolutionary when they were first built over a decade ago, a “missing link” in electronics to supplement the resistor, capacitor and inductor. They have since been manufactured commercially in memory devices, but the research team say they could be used to develop AI systems within the next three years.
Memristors offer vastly improved efficiency because they operate not just in a binary code of ones and zeros, but at multiple levels between zero and one at the same time, meaning more information can be packed into each bit.
Moreover, memristors are often described as a neuromorphic (brain-inspired) form of computing because, like in the brain, processing and memory are implemented in the same adaptive building blocks, in contrast to current computer systems that waste a lot of energy in data movement.
In the study, Dr Adnan Mehonic, PhD student Dovydas Joksas (both UCL Electronic & Electrical Engineering), and colleagues from the UK and the US tested the new approach in several different types of memristors and found that it improved the accuracy of all of them, regardless of material or particular memristor technology. It also worked for a number of different problems that may affect memristors’ accuracy.
Researchers found that their approach increased the accuracy of the neural networks for typical AI tasks to a comparable level to software tools run on conventional digital hardware.
Dr Mehonic, director of the study, said: “We hoped that there might be more generic approaches that improve not the device-level, but the system-level behaviour, and we believe we found one. Our approach shows that, when it comes to memristors, several heads are better than one. Arranging the neural network into several smaller networks rather than one big network led to greater accuracy overall.”
Dovydas Joksas further explained: “We borrowed a popular technique from computer science and applied it in the context of memristors. And it worked! Using preliminary simulations, we found that even simple averaging could significantly increase the accuracy of memristive neural networks.”
Professor Tony Kenyon (UCL Electronic & Electrical Engineering), a co-author on the study, added: “We believe now is the time for memristors, on which we have been working for several years, to take a leading role in a more energy-sustainable era of IoT devices and edge computing.”
The Latest Updates from Bing News & Google News
Go deeper with Bing News on:
Energy-efficient artificial intelligence
- NVIDIA Announces Technology For Training Giant Artificial Intelligence Modelson April 12, 2021 at 4:21 pm
NVIDIA GTC is the premier annual conference for developers, scientists, and businesses interested in machine learning or artificial intelligence ... also important to note that LDDR is 10X more energy ...
- Johnson Controls and Pelion Partner on Artificial Intelligence/Internet of Things (AIoT)on April 8, 2021 at 2:16 pm
Johnson Controls and Pelion AIoT partnership focuses on smart, healthy and sustainable buildings using OpenBlue technology.
- Johnson Controls and Pelion Partner on Artificial Intelligence / Internet of Things (AIoT) For Smart, Healthy, and Sustainable Buildingson April 8, 2021 at 6:00 am
Pelion, the Connected IoT Device service provider, and subsidiary of Arm, jointly announced a partnership with Johnson Controls (NYSE: JCI), the global leader for smart, healthy and sustainable ...
- Artificial Intelligence in Energy Market 2021 with Top Countries Data : Potential Growth, Share, Size, Trend, and Analysis of Key Playerson April 8, 2021 at 4:30 am
(MENAFN - GetNews) Increasing need to obtain operational efficiency to meet energy requirements are key factors driving global Artificial Intelligence in energy market growth. Market Size USD 3.82 ...
- UNESCO Director-General and President of Slovenia inaugurate first research centre on artificial intelligenceon April 6, 2021 at 5:04 am
The Director-General of UNESCO called for countries, organizations and individuals to combine their energy and propose solutions so that ...
Go deeper with Google Headlines on:
Energy-efficient artificial intelligence
Go deeper with Bing News on:
Memristors powering AI
- Intrinsic closes GBP 1.35m seed funding round to prototype next generation memory deviceson April 8, 2021 at 8:42 am
Memory innovator Intrinsic Semiconductor Technologies Ltd (“Intrinsic”) has announced the close of a £1.35m seed funding round led by investors UCL Technology Fund and IP Group plc.
- Startup Funding: March 2021on April 7, 2021 at 12:03 am
It was also a good month for startups making chips for AI acceleration, with four companies from seed to Series D stages raising funds. Plus, two companies are looking to shake up the memory and ...
- Memristor Computing On A Chipon March 24, 2021 at 4:59 pm
researchers at the University of Michigan are claiming the first memristor-based programmable computer that has the potential to make AI applications more efficient and faster. Because memristors ...
- New theory unveils obscure nonvolatile resistive switching in 2D materialson March 24, 2021 at 1:05 am
This architecture has served the purpose so far until we embarked on the era of artificial intelligence (AI ... 2D memristors can overcome the vertical scaling obstacle of oxide-based devices and ...
- AI Computing Hardware Market Size, Analysis by Growth, Emerging, Trends and Future, Opportunities Till 2025on March 22, 2021 at 5:21 pm
This kind of design could lead to unconventional circuits based on emerging nanotechnology like memristors ... highly-advanced AI processing for small and low-power edge computing devices.