# Backpropagation through nonlinear units for all-optical training of neural networks

Source: [Backpropagation through nonlinear units for all-optical training of neural networks](<https://www.sota2.com/research/paper/68fa3e641e209131ce8e727a>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2025-10-25T01:58:13.075Z

Authors: Xianxin Guo, Thomas D. Barrett, Zhiming M. Wang, A. I. Lvovsky

Published: 2019-12-23T10:14:53.000Z

## Abstract

Backpropagation through nonlinear neurons is an outstanding challenge to the field of optical neural networks and the major conceptual barrier to all-optical training schemes. Each neuron is required to exhibit a directionally dependent response to propagating optical signals, with the backwards response conditioned on the forward signal, which is highly non-trivial to implement optically. We propose a practical and surprisingly simple solution that uses saturable absorption to provide the network nonlinearity. We find that the backward propagating gradients required to train the network can be approximated in a pump-probe scheme that requires only 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 approximations. This scheme is compatible with leading optical neural network proposals and therefore provides a feasible path towards end-to-end optical training.

## Recorded benchmark results

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

## Original sources and implementation

[Original paper](<https://arxiv.org/abs/1912.12256>)

[PDF](<https://arxiv.org/pdf/1912.12256.pdf>)
