Deep physical neural networks trained with backpropagation
By Logan G. Wright, Tatsuhiro Onodera, Martin M. Stein, Darren T. Schachter, Zoey Hu, Peter Leonard McMahon. Nature, 2021
729 citations recorded by the source corpus.
Deep-learning models have become pervasive tools in science and engineering. However, their energy requirements now increasingly limit their scalability1. Deep-learning accelerators2–9 aim to perform deep learning energy-efficiently, usually targeting the inference phase and often by exploiting physical substrates beyond conventional electronics. Approaches so far10–22 have been unable to apply the backpropagation algorithm to train unconventional novel hardware in situ. The advantages of backpropagation have made it the de facto training method for large-scale neural networks, so this deficiency constitutes a major impediment. Here we introduce a hybrid in situ–in silico algorithm, called physics-aware training, that applies backpropagation to train controllable physical systems. Just as deep learning realizes computations with deep neural networks made from layers of mathematical functions, our approach allows us to train deep physical neural networks made from layers of controllable physical systems, even when the physical layers lack any mathematical isomorphism to conventional artificial neural network layers. To demonstrate the universality of our approach, we train diverse physical neural networks based on optics, mechanics and electronics to experimentally perform audio and image classification tasks. Physics-aware training combines the scalability of backpropagation with the automatic mitigation of imperfections and noise achievable with in situ algorithms. Physical neural networks have the potential to perform machine learning faster and more energy-efficiently than conventional electronic processors and, more broadly, can endow physical systems with automatically designed physical functionalities, for example, for robotics23–26, materials27–29 and smart sensors30–32. A hybrid algorithm that applies backpropagation is used to train layers of controllable physical systems to carry out calculations like deep neural networks, but accounting for real-world noise and imperfections.
Subfields: Artificial Intelligence, Electrical and Electronic Engineering, Statistical and Nonlinear Physics
View Paper: https://www.semanticscholar.org/paper/8708abfc6a5d80c1d2bbd911677e2f8940040a4c
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Artificial Intelligence
In Electrical and Electronic Engineering
In Statistical and Nonlinear Physics
Citations in the corpus
- The physics of optical computing (2023, methodology): “1b) — not just individually (that is, element-wise) but also with operations that, for example, add or multiply data in different frequency modes 17 .”