Supervised Learning in Temporally-Coded Spiking Neural Networks with Approximate Backpropagation

TL;DR

This paper introduces a new supervised learning method for temporally-encoded spiking neural networks that uses a reinforcement signal similar to backpropagation, achieving comparable performance to traditional methods with less computational effort.

Contribution

The paper presents a novel, computationally efficient supervised learning rule for multilayer spiking neural networks that enables effective classification tasks.

Findings

Achieved MNIST digit classification accuracy comparable to non-spiking networks.

Developed a local data-based weight update rule with a reinforcement signal.

Produced specific output spike trains by adjusting spike timing.

Abstract

In this work we propose a new supervised learning method for temporally-encoded multilayer spiking networks to perform classification. The method employs a reinforcement signal that mimics backpropagation but is far less computationally intensive. The weight update calculation at each layer requires only local data apart from this signal. We also employ a rule capable of producing specific output spike trains; by setting the target spike time equal to the actual spike time with a slight negative offset for key high-value neurons the actual spike time becomes as early as possible. In simulated MNIST handwritten digit classification, two-layer networks trained with this rule matched the performance of a comparable backpropagation based non-spiking network.