Supervised Learning of Logical Operations in Layered Spiking Neural Networks with Spike Train Encoding

TL;DR

This paper demonstrates that layered spiking neural networks can learn logical operations, including XOR, using supervised training with spike train encoding and the ReSuMe algorithm, advancing understanding of spike-based computation.

Contribution

It shows that ReSuMe can be effectively combined with multiplicative scaling to train layered spiking neural networks on logical tasks, including XOR.

Findings

Layered networks with one hidden layer can learn XOR.

Networks without hidden layers cannot learn XOR.

Supervised learning in spiking networks enhances understanding of spike train computations.

Abstract

Few algorithms for supervised training of spiking neural networks exist that can deal with patterns of multiple spikes, and their computational properties are largely unexplored. We demonstrate in a set of simulations that the ReSuMe learning algorithm can be successfully applied to layered neural networks. Input and output patterns are encoded as spike trains of multiple precisely timed spikes, and the network learns to transform the input trains into target output trains. This is done by combining the ReSuMe learning algorithm with multiplicative scaling of the connections of downstream neurons. We show in particular that layered networks with one hidden layer can learn the basic logical operations, including Exclusive-Or, while networks without hidden layer cannot, mirroring an analogous result for layered networks of rate neurons. While supervised learning in spiking neural networks is not yet fit for technical purposes, exploring computational properties of spiking neural networks advances our understanding of how computations can be done with spike trains.