Bayesian Continual Learning via Spiking Neural Networks

TL;DR

This paper introduces a Bayesian continual learning framework for spiking neural networks, enabling energy-efficient, adaptive neuromorphic systems with well-calibrated uncertainty estimates, demonstrated on Intel's Lava platform.

Contribution

It develops online Bayesian learning rules for SNNs that quantify uncertainty and adapt to changing tasks, a novel approach in neuromorphic engineering.

Findings

Bayesian SNNs outperform frequentist models in adaptation.

The approach effectively quantifies uncertainty in learning.

Experimental validation on Intel's Lava platform shows promising results.

Abstract

Among the main features of biological intelligence are energy efficiency, capacity for continual adaptation, and risk management via uncertainty quantification. Neuromorphic engineering has been thus far mostly driven by the goal of implementing energy-efficient machines that take inspiration from the time-based computing paradigm of biological brains. In this paper, we take steps towards the design of neuromorphic systems that are capable of adaptation to changing learning tasks, while producing well-calibrated uncertainty quantification estimates. To this end, we derive online learning rules for spiking neural networks (SNNs) within a Bayesian continual learning framework. In it, each synaptic weight is represented by parameters that quantify the current epistemic uncertainty resulting from prior knowledge and observed data. The proposed online rules update the distribution parameters in a streaming fashion as data are observed. We instantiate the proposed approach for both real-valued and binary synaptic weights. Experimental results using Intel's Lava platform show the merits of Bayesian over frequentist learning in terms of capacity for adaptation and uncertainty quantification.