A spiking photonic neural network of 40.000 neurons, trained with rank-order coding for leveraging sparsity

TL;DR

This paper demonstrates a large-scale photonic spiking neural network with 40,000 neurons, leveraging sparsity and novel training methods to achieve high accuracy on MNIST while using a fraction of the neurons.

Contribution

It introduces a scalable photonic SNN architecture with 40,000 neurons, employing a modified Ikeda map and SPSA training, advancing photonic neuromorphic computing.

Findings

Achieved 83.5% accuracy on MNIST with 22% neuron utilization.

First use of SPSA algorithm in photonic neural network training.

Demonstrated scalable, cost-effective photonic SNN with off-the-shelf components.

Abstract

Spiking neural networks are neuromorphic systems that emulate certain aspects of biological neurons, offering potential advantages in energy efficiency and speed by for example leveraging sparsity. While CMOS-based electronic SNN hardware has shown promise, scalability and parallelism challenges remain. Photonics provides a promising platform for SNNs due to the speed of excitable photonic devices standing in as neurons and the parallelism and low-latency of optical signal conduction. Here, we present a photonic SNN comprising 40,000 neurons using off-the-shelf components, including a spatial light modulator and a CMOS camera, enabling scalable and cost-effective implementations for photonic SNN proof of concept studies. The system is governed by a modified Ikeda map, were adding additional inhibitory feedback forcing introduces excitability akin to biological dynamics. Using latency encoding and sparsity, the network achieves 83.5% accuracy on MNIST using 22% of neurons, and 77.5% with 8.5% neuron utilization. Training is performed via liquid state machine concepts combined with the hardware-compatible SPSA algorithm, marking its first use in photonic neural networks. This demonstration integrates photonic nonlinearity, excitability, and sparse computation, paving the way for efficient large-scale photonic neuromorphic systems.