Skip to yearly menu bar Skip to main content


In-Person Poster presentation / poster accept

Heterogeneous Neuronal and Synaptic Dynamics for Spike-Efficient Unsupervised Learning: Theory and Design Principles

Biswadeep Chakraborty · Saibal Mukhopadhyay

MH1-2-3-4 #163

Keywords: [ STDP ] [ Heterogeneity ] [ LIF ] [ spike efficiency ] [ memory capacity ] [ spiking neural network ] [ theory ] [ bayesian optimization ] [ Unsupervised and Self-supervised learning ]


Abstract: This paper shows that the heterogeneity in neuronal and synaptic dynamics reduces the spiking activity of a Recurrent Spiking Neural Network (RSNN) while improving prediction performance, enabling spike-efficient (unsupervised) learning.We analytically show that the diversity in neurons' integration/relaxation dynamics improves an RSNN's ability to learn more distinct input patterns (higher memory capacity), leading to improved classification and prediction performance. We further prove that heterogeneous Spike-Timing-Dependent-Plasticity (STDP) dynamics of synapses reduce spiking activity but preserve memory capacity. The analytical results motivate Heterogeneous RSNN design using Bayesian optimization to determine heterogeneity in neurons and synapses to improve $\mathcal{E}$, defined as the ratio of spiking activity and memory capacity. The empirical results on time series classification and prediction tasks show that optimized HRSNN increases performance and reduces spiking activity compared to a homogeneous RSNN.

Chat is not available.