Local learning through propagation delays in spiking neural networks

TL;DR

This paper introduces a local learning rule based on activity-dependent spike propagation delays in spiking neural networks, enhancing classification accuracy and generalization in a digit recognition task.

Contribution

It presents a novel local plasticity rule that adjusts spike propagation times, improving learning and generalization in spiking neural networks.

Findings

Networks improve classification accuracy after training.

Training enables generalization to unseen input classes.

Method leverages spike timing sequences for enhanced memory capacity.

Abstract

We propose a novel local learning rule for spiking neural networks in which spike propagation times undergo activity-dependent plasticity. Our plasticity rule aligns pre-synaptic spike times to produce a stronger and more rapid response. Inputs are encoded by latency coding and outputs decoded by matching similar patterns of output spiking activity. We demonstrate the use of this method in a three-layer feedfoward network with inputs from a database of handwritten digits. Networks consistently improve their classification accuracy after training, and training with this method also allowed networks to generalize to an input class unseen during training. Our proposed method takes advantage of the ability of spiking neurons to support many different time-locked sequences of spikes, each of which can be activated by different input activations. The proof-of-concept shown here demonstrates the great potential for local delay learning to expand the memory capacity and generalizability of spiking neural networks.