Pre-Synaptic Pool Modification (PSPM): A Supervised Learning Procedure for Spiking Neural Networks

TL;DR

This paper introduces PSPM, a supervised learning method for spiking neural networks that enhances spike train similarity without requiring gradient information, but does not necessarily recover ground truth weights.

Contribution

The paper presents PSPM, a novel heuristic supervised learning rule for SNNs that improves spike train similarity without gradient calculations and explores its implications for connectome inference.

Findings

PSPM improves spike train similarity in all-to-all SNNs.

Learned weights often differ from ground truth, indicating limitations in connectome inference.

Spike train similarity is sensitive to local updates, but other activity measures can be learned.

Abstract

Learning synaptic weights of spiking neural network (SNN) models that can reproduce target spike trains from provided neural firing data is a central problem in computational neuroscience and spike-based computing. The discovery of the optimal weight values can be posed as a supervised learning task wherein the weights of the model network are chosen to maximize the similarity between the target spike trains and the model outputs. It is still largely unknown whether optimizing spike train similarity of highly recurrent SNNs produces weight matrices similar to those of the ground truth model. To this end, we propose flexible heuristic supervised learning rules, termed Pre-Synaptic Pool Modification (PSPM), that rely on stochastic weight updates in order to produce spikes within a short window of the desired times and eliminate spikes outside of this window. PSPM improves spike train similarity for all-to-all SNNs and makes no assumption about the post-synaptic potential of the neurons or the structure of the network since no gradients are required. We test whether optimizing for spike train similarity entails the discovery of accurate weights and explore the relative contributions of local and homeostatic weight updates. Although PSPM improves similarity between spike trains, the learned weights often differ from the weights of the ground truth model, implying that connectome inference from spike data may require additional constraints on connectivity statistics. We also find that spike train similarity is sensitive to local updates, but other measures of network activity such as avalanche distributions, can be learned through synaptic homeostasis.