In a groundbreaking and game-changing study that could revolutionize the field of artificial intelligence, researchers have successfully demonstrated that photonic chips can be utilized to train neural networks using on-chip backpropagation—the most widely used method for training these complex systems.
This astonishing breakthrough paves the way for the development of futuristic, optically driven, and energy-efficient machine learning technologies, which hold the potential to dramatically reduce the carbon footprint and costs associated with AI computation.
Neural networks, an approach to machine learning conceptually inspired by the miraculous biology of the human brain, have emerged as the cornerstone of many cutting-edge scientific and commercial AI technologies, including the much-talked-about ChatGPT architectures. As neural networks continue to make significant strides and become increasingly ubiquitous, the energy required to power these awe-inspiring technologies is expected to skyrocket, perhaps doubling every 5-6 months, as some staggering estimates suggest.
Faced with such rapidly increasing energy demands, the quest for more energy-efficient hardware solutions, such as photonic neural networks, has become a critical priority for researchers worldwide. A crucial step towards effectively integrating photonic circuits into neural network applications is the development of a photonic implementation for the so-called backpropagation, the gold standard in neural network training methods.
In a monumental leap forward, Sunil Pai and colleagues have designed and brought to life a cutting-edge hybrid photonic neural network (PNN) chip, capable of performing lightning-fast and efficient on-chip backpropagation training. Employing their state-of-the-art, multilayer photonic integrated circuit, Pai et al. conducted in situ backpropagation training by sending light-encoded errors backwards through the photonic neural network and measuring the optical interference with the original forward-going “inference” signal.
In a series of meticulously designed proof-of-principle experiments, the authors discovered that the PNN performed on par with digital neural network platforms, heralding a new era for scalable, energy-efficient on-chip machine learning. Charles Roques-Carmes, in a thought-provoking and insightful perspective, writes, “Photonic networks are now becoming competitive with state-of-the-art digital platforms, in terms of speed and energy efficiency.”
With this groundbreaking study, it is now anticipated that, in just a few years, large-scale hybrid and all-optical photonic chips will challenge their electronic counterparts in the realm of inference and learning of real-world AI tasks. This pioneering research has the potential to transform the landscape of artificial intelligence, opening up new possibilities for more sustainable and efficient AI technologies that will shape the future of our world.
Original Article: Backpropagation training achieved in photonic neural network
More from: Polytechnic University of Milan
The Latest Updates from Bing News
Go deeper with Bing News on:
- Fingernail Chip Implants? West Virginia's CISO Sees Value
And in just the past few months, Elon Musk's brain chip firm, Neuralink, received approval from the U.S. Food and Drug Administration to conduct its first tests on humans. Closer to home for many ...
- Design Your Own Chip With TinyTapeout
His latest effort to involve the hacker community, TinyTapeout, makes chip design accessible to newcomers – the bar is as low as arranging logic gates on a web browser page. Just six of the ...
- Beginner’s Look At On-Chip Debugging
As your embedded applications get more complicated an On-Chip Debugger will save you a lot of time when things don’t run quite right. On-Chip Debugging (OCD) is just what it sounds like — a ...
- 'Lab-on-a-chip' can tell the difference between COVID and the flu
The new "lab-on-a-chip" testing technology builds on a silicon complementary metal oxide semiconductor-compatible, photonic chip-based platform Chen and his team have been developing for several ...
- New 3D stretchable electronics can advance organ-on-chip technology
Flexible electronic nanomembranes show promise for revolutionary organ-on-chip technologies, potentially reducing the need for animal testing in medical research. Engineers from UNSW Sydney have ...
Go deeper with Bing News on:
Photonic neural networks
- Research Bits: June 5
Improving memristors, organic electrochemical transistors, high-speed thin-film lithium niobate quantum processor.
- Training A Neural Network To Play A Driving Game
In these cases, it can make more sense to create a neural network and train the computer to do the job, as one would a human. On a more basic level, [Gigante] did just that, teaching a neural ...
- Lightmatter’s photonic AI hardware is ready to shine with $154M in new funding
Photonic computing startup Lightmatter is taking its big shot at the rapidly growing AI computation market with a hardware-software combo it claims will help the industry level up — and save a lot of ...
- Neural Network Keeps It Light
Researchers at Princeton have announced the first photonic neural network. We recently talked about how artificial neurons work in conventional hardware and software. The artificial neurons look ...
- Greek researchers build the fastest artificial intelligence photo-processor in the world
An important achievement in the field of information processing using photonic technology and neural networks is presented by a scientific group of the Department of Informatics of the Aristotle ...