Ensemble plasticity and network adaptability in SNNs

TL;DR

This paper introduces a novel ensemble learning method based on entropy and network activation, combined with spike-rate neuron pruning driven by spiking activity, to improve the efficiency and robustness of artificial spiking neural networks, especially in low-resource scenarios.

Contribution

The paper proposes a new ensemble learning approach and spike-based pruning technique that utilize spiking activity for better network regulation and efficiency in ASNNs.

Findings

Pruning low spike-rate neurons enhances generalization.

Neurons form hierarchical clusters based on spiking rate during learning.

The method improves robustness in low-resource environments.

Abstract

Artificial Spiking Neural Networks (ASNNs) promise greater information processing efficiency because of discrete event-based (i.e., spike) computation. Several Machine Learning (ML) applications use biologically inspired plasticity mechanisms as unsupervised learning techniques to increase the robustness of ASNNs while preserving efficiency. Spike Time Dependent Plasticity (STDP) and Intrinsic Plasticity (IP) (i.e., dynamic spiking threshold adaptation) are two such mechanisms that have been combined to form an ensemble learning method. However, it is not clear how this ensemble learning should be regulated based on spiking activity. Moreover, previous studies have attempted threshold based synaptic pruning following STDP, to increase inference efficiency at the cost of performance in ASNNs. However, this type of structural adaptation, that employs individual weight mechanisms, does not consider spiking activity for pruning which is a better representation of input stimuli. We envisaged that plasticity-based spike-regulation and spike-based pruning will result in ASSNs that perform better in low resource situations. In this paper, a novel ensemble learning method based on entropy and network activation is introduced, which is amalgamated with a spike-rate neuron pruning technique, operated exclusively using spiking activity. Two electroencephalography (EEG) datasets are used as the input for classification experiments with a three-layer feed forward ASNN trained using one-pass learning. During the learning process, we observed neurons assembling into a hierarchy of clusters based on spiking rate. It was discovered that pruning lower spike-rate neuron clusters resulted in increased generalization or a predictable decline in performance.