Biologically Plausible Learning of Text Representation with Spiking Neural Networks

TL;DR

This paper introduces a biologically plausible spiking neural network model trained with STDP to generate low-dimensional spike-based text representations, achieving competitive classification accuracy on the 20 newsgroups dataset.

Contribution

It presents a novel biologically plausible method for text representation using SNNs trained with STDP, enabling effective text classification.

Findings

Achieved 80.19% accuracy on 20 newsgroups dataset.

Demonstrated effective low-dimensional spike-based text representation.

Validated biological plausibility of the learning mechanism.

Abstract

This study proposes a novel biologically plausible mechanism for generating low-dimensional spike-based text representation. First, we demonstrate how to transform documents into series of spikes spike trains which are subsequently used as input in the training process of a spiking neural network (SNN). The network is composed of biologically plausible elements, and trained according to the unsupervised Hebbian learning rule, Spike-Timing-Dependent Plasticity (STDP). After training, the SNN can be used to generate low-dimensional spike-based text representation suitable for text/document classification. Empirical results demonstrate that the generated text representation may be effectively used in text classification leading to an accuracy of $80.19\%$ on the bydate version of the 20 newsgroups data set, which is a leading result amongst approaches that rely on low-dimensional text representations.