Dynamic Weight Adaptation in Spiking Neural Networks Inspired by Biological Homeostasis

TL;DR

This paper introduces a biologically inspired dynamic weight adaptation mechanism for spiking neural networks, enabling real-time homeostasis regulation that improves robustness and performance in control tasks under various conditions.

Contribution

It presents the first integration of BCM-inspired homeostatic regulation into SNNs, enhancing their stability and performance without extensive fine-tuning.

Findings

DWAM improves SNN performance under degraded conditions.

DWAM enhances existing homeostatic mechanisms in SNNs.

Experimental validation in obstacle avoidance and control tasks.

Abstract

Homeostatic mechanisms play a crucial role in maintaining optimal functionality within the neural circuits of the brain. By regulating physiological and biochemical processes, these mechanisms ensure the stability of an organism's internal environment, enabling it to better adapt to external changes. Among these mechanisms, the Bienenstock, Cooper, and Munro (BCM) theory has been extensively studied as a key principle for maintaining the balance of synaptic strengths in biological systems. Despite the extensive development of spiking neural networks (SNNs) as a model for bionic neural networks, no prior work in the machine learning community has integrated biologically plausible BCM formulations into SNNs to provide homeostasis. In this study, we propose a Dynamic Weight Adaptation Mechanism (DWAM) for SNNs, inspired by the BCM theory. DWAM can be integrated into the host SNN, dynamically adjusting network weights in real time to regulate neuronal activity, providing homeostasis to the host SNN without any fine-tuning. We validated our method through dynamic obstacle avoidance and continuous control tasks under both normal and specifically designed degraded conditions. Experimental results demonstrate that DWAM not only enhances the performance of SNNs without existing homeostatic mechanisms under various degraded conditions but also further improves the performance of SNNs that already incorporate homeostatic mechanisms.