# Training Large-Scale Optical Neural Networks with Two-Pass Forward Propagation

arXiv: https://arxiv.org/abs/2408.08337 · HTML: https://mlsanity.com/paper/2408.08337/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 8 of its 16 references that are in the map.
- First posted on arXiv 15 Aug 2024.

## Builds on (most cited first, 8 of 8)

- [A Survey on Evaluation of Large Language Models](https://mlsanity.com/paper/2307.03109/) (2023)
- [The Forward-Forward Algorithm: Some Preliminary Investigations](https://mlsanity.com/paper/2212.13345/) (2022)
- [Error-driven Input Modulation: Solving the Credit Assignment Problem without a Backward Pass](https://mlsanity.com/paper/2201.11665/) (2022)
- [Training of photonic neural networks through in situ backpropagation](https://mlsanity.com/paper/1805.09943/) (2018)
- [Forward-Forward Training of an Optical Neural Network](https://mlsanity.com/paper/2305.19170/) (2023)
- [Backpropagation through nonlinear units for all-optical training of neural networks](https://mlsanity.com/paper/1912.12256/) (2019)
- [TACNET: Temporal Audio Source Counting Network](https://mlsanity.com/paper/2311.02369/) (2023)
- [Free-Space Optical Spiking Neural Network](https://mlsanity.com/paper/2311.04558/) (2023)

## Abstract (arXiv)

This paper addresses the limitations in Optical Neural Networks (ONNs) related to training efficiency, nonlinear function implementation, and large input data processing. We introduce Two-Pass Forward Propagation, a novel training method that avoids specific nonlinear activation functions by modulating and re-entering error with random noise. Additionally, we propose a new way to implement convolutional neural networks using simple neural networks in integrated optical systems. Theoretical foundations and numerical results demonstrate significant improvements in training speed, energy efficiency, and scalability, advancing the potential of optical computing for complex data tasks.