Photonics Research · 2021 · 88 citations · 36 references
ComputingComputer ScienceMachine LearningOpticsPhotonicsDeep LearningNeural NetworksNonlinear Optical MaterialsNonlinear OpticsBackpropagationConvolutional Neural NetworksNonlinear AbsorptionNonlinear Optical Signal ProcessingOptical Neural NetworksOptical NonlinearityPassive Optical NetworksSaturable Absorption Models
We propose a practical scheme for end-to-end optical backpropagation in neural networks. Using saturable absorption for the nonlinear units, we find that the backward-propagating gradients required to train the network can be approximated in a surprisingly simple pump-probe scheme that requires only simple passive optical elements. Simulations show that, with readily obtainable optical depths, our approach can achieve equivalent performance to state-of-the-art computational networks on image classification benchmarks, even in deep networks with multiple sequential gradient approximation. With backpropagation through nonlinear units being an outstanding challenge to the field, this work provides a feasible path toward truly all-optical neural networks.
36
Gradient-based learning applied to document recognition
Yann LeCun, Léon Bottou, Yoshua Bengio et al. · Proceedings of the IEEE · 1998 · 58.2K citations · Full text
Multilayer feedforward networks are universal approximators
Kurt Hornik, Maxwell B. Stinchcombe, Halbert White · Neural Networks · 1989 · 21.2K citations
Mastering the game of Go with deep neural networks and tree search
David Silver, Aja Huang, Chris J. Maddison et al. · Nature · 2016 · 15.8K citations