Spike Timing Dependent Competitive Learning in Recurrent Self Organizing Pulsed Neural Networks Case Study: Phoneme and Word Recognition

TL;DR

This paper introduces three variants of self-organizing maps using spike-timing dependent plasticity for unsupervised learning, demonstrating their effectiveness in phoneme and word recognition tasks in continuous speech.

Contribution

It presents novel SOM models with spike-timing dependent Hebbian learning for unsupervised sequence classification, specifically applied to speech recognition.

Findings

Effective phoneme classification in continuous speech

Speaker-independent word recognition achieved

Demonstrated advantages of spike-timing based learning in neural networks

Abstract

Synaptic plasticity seems to be a capital aspect of the dynamics of neural networks. It is about the physiological modifications of the synapse, which have like consequence a variation of the value of the synaptic weight. The information encoding is based on the precise timing of single spike events that is based on the relative timing of the pre- and post-synaptic spikes, local synapse competitions within a single neuron and global competition via lateral connections. In order to classify temporal sequences, we present in this paper how to use a local hebbian learning, spike-timing dependent plasticity for unsupervised competitive learning, preserving self-organizing maps of spiking neurons. In fact we present three variants of self-organizing maps (SOM) with spike-timing dependent Hebbian learning rule, the Leaky Integrators Neurons (LIN), the Spiking_SOM and the recurrent Spiking_SOM (RSSOM) models. The case study of the proposed SOM variants is phoneme classification and word recognition in continuous speech and speaker independent.