# Ensemble plasticity and network adaptability in SNNs

arXiv: https://arxiv.org/abs/2203.07039 · HTML: https://mlsanity.com/paper/2203.07039/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 11 of its 73 references that are in the map.
- First posted on arXiv 11 Mar 2022.

## Builds on (most cited first, 11 of 11)

- [LSTM: A Search Space Odyssey](https://mlsanity.com/paper/1503.04069/) (2015)
- [Deep Learning in Spiking Neural Networks](https://mlsanity.com/paper/1804.08150/) (2018)
- [Neural Architecture Search without Training](https://mlsanity.com/paper/2006.04647/) (2020)
- [Training Deep Spiking Neural Networks using Backpropagation](https://mlsanity.com/paper/1608.08782/) (2016)
- [STDP Based Pruning of Connections and Weight Quantization in Spiking Neural Networks for Energy Efficient Recognition](https://mlsanity.com/paper/1710.04734/) (2017)
- [A Biologically Plausible Supervised Learning Method for Spiking Neural Networks Using the Symmetric STDP Rule](https://mlsanity.com/paper/1812.06574/) (2018)
- [Automatic Analysis of EEGs Using Big Data and Hybrid Deep Learning Architectures](https://mlsanity.com/paper/1712.09771/) (2017)
- [A Neural Architecture Search based Framework for Liquid State Machine Design](https://mlsanity.com/paper/2004.07864/) (2020)
- [Skip-Connected Self-Recurrent Spiking Neural Networks with Joint Intrinsic Parameter and Synaptic Weight Training](https://mlsanity.com/paper/2010.12691/) (2020)
- [An Online Unsupervised Structural Plasticity Algorithm for Spiking Neural Networks](https://mlsanity.com/paper/1512.01314/) (2015)
- [Composing Recurrent Spiking Neural Networks using Locally-Recurrent Motifs and Risk-Mitigating Architectural Optimization](https://mlsanity.com/paper/2108.01793/) (2021)

## Abstract (arXiv)

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.