Continual Learning with Columnar Spiking Neural Networks

TL;DR

This paper introduces columnar spiking neural networks with local learning rules that effectively enable continual learning, reducing catastrophic forgetting and maintaining high accuracy across multiple sequential tasks.

Contribution

It presents a biologically plausible SNN model with local learning rules that balances stability and plasticity for continual learning, demonstrating effectiveness on benchmark datasets.

Findings

Achieves 92% accuracy on each task after sequential learning

Maintains only 4% performance degradation on initial task

Effectively learns ten sequential tasks with low forgetting

Abstract

Continual learning is a key feature of biological neural systems, but artificial neural networks often suffer from catastrophic forgetting. Instead of backpropagation, biologically plausible learning algorithms may enable stable continual learning. This study proposes columnar-organized spiking neural networks (SNNs) with local learning rules for continual learning and catastrophic forgetting. Using CoLaNET (Columnar Layered Network), we show that its microcolumns adapt most efficiently to new tasks when they lack shared structure with prior learning. We demonstrate how CoLaNET hyperparameters govern the trade-off between retaining old knowledge (stability) and acquiring new information (plasticity). We evaluate CoLaNET on two benchmarks: Permuted MNIST (ten sequential pixel-permuted tasks) and a two-task MNIST/EMNIST setup. Our model learns ten sequential tasks effectively, maintaining 92% accuracy on each. It shows low forgetting, with only 4% performance degradation on the first task after training on nine subsequent tasks.