SNN-LPCG: Spiking Neural Networks with Local Plasticity Context Gating for Lifelong Learning

Jiangrong Shen, Wenyao Ni, Qi Xu, Gang Pan, Huajin Tang

Keywords: Spiking neural networks, context gating, lifelong learning

Abstract: Humans learn multiple tasks in succession with minimal mutual interference, through the context gating mechanism in the prefrontal cortex (PFC). The brain-inspired models of spiking neural networks (SNNs) have drawn massive attention for their energy efficiency and biological plausibility. To overcome catastrophic forgetting when learning multiple tasks in sequence, current SNNs for lifelong learning focus on memory reserving or regularization-based modification, while ignoring the cognitive control behavior in the brain. Inspired by biological context-dependent gating mechanisms found in PFC, we propose SNNs with context gating trained by the local plasticity rule (SNN-LPCG) for lifelong learning. The iterative training between global and local plasticity for task units is designed to strengthen the connections between task neurons and hidden neurons and preserve the multi-task relevant information. The experiments show that the proposed model is effective in maintaining the past learning experience and has better task-selectivity than other methods during lifelong learning. Our results provide new insights that the SNN-LPCG model is able to extend context gating with good scalability on different SNN architectures. Thus, our models have good potential for parallel implementation on neuromorphic hardware for real-life tasks.

Primary Area: applications to neuroscience & cognitive science

Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.

Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.

Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.

No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.

Submission Number: 2612