Scalability of all-optical neural networks based on spatial light modulators

TL;DR

This paper demonstrates a scalable all-optical neural network using spatial light modulators, analyzing error propagation and confirming its potential for large-scale applications like digit recognition.

Contribution

It introduces a scalable AODNN with programmable operations and verifies its scalability and practical recognition capabilities.

Findings

Errors propagate but remain manageable in large networks

The network successfully recognizes handwritten digits and fashion items

Scalability is confirmed through error analysis and experimental validation

Abstract

Optical implementation of artificial neural networks has been attracting great attention due to its potential in parallel computation at speed of light. Although all-optical deep neural networks (AODNNs) with a few neurons have been experimentally demonstrated with acceptable errors recently, the feasibility of large scale AODNNs remains unknown because error might accumulate inevitably with increasing number of neurons and connections. Here, we demonstrate a scalable AODNN with programmable linear operations and tunable nonlinear activation functions. We verify its scalability by measuring and analyzing errors propagating from a single neuron to the entire network. The feasibility of AODNNs is further confirmed by recognizing handwritten digits and fashions respectively.