BiSNN: Training Spiking Neural Networks with Binary Weights via Bayesian Learning

TL;DR

This paper introduces BiSNN, a spiking neural network model with binary weights and activations, leveraging Bayesian learning to improve energy efficiency and accuracy over traditional full-precision models.

Contribution

It proposes a novel Bayesian learning approach for training binary-weight SNNs, combining energy-efficient computation with improved accuracy and calibration.

Findings

Bayesian paradigm enhances accuracy and calibration.

Binary weights and activations reduce energy consumption.

Performance loss is minimal compared to full-precision models.

Abstract

Artificial Neural Network (ANN)-based inference on battery-powered devices can be made more energy-efficient by restricting the synaptic weights to be binary, hence eliminating the need to perform multiplications. An alternative, emerging, approach relies on the use of Spiking Neural Networks (SNNs), biologically inspired, dynamic, event-driven models that enhance energy efficiency via the use of binary, sparse, activations. In this paper, an SNN model is introduced that combines the benefits of temporally sparse binary activations and of binary weights. Two learning rules are derived, the first based on the combination of straight-through and surrogate gradient techniques, and the second based on a Bayesian paradigm. Experiments validate the performance loss with respect to full-precision implementations, and demonstrate the advantage of the Bayesian paradigm in terms of accuracy and calibration.