A Study of Biologically Plausible Neural Network: The Role and Interactions of Brain-Inspired Mechanisms in Continual Learning

TL;DR

This paper explores a biologically plausible neural network framework incorporating brain-inspired mechanisms like sparse representations, Hebbian learning, and replay to improve continual learning and mitigate catastrophic forgetting.

Contribution

It introduces a biologically plausible architecture with excitatory and inhibitory neurons, integrating multiple brain-inspired mechanisms for continual learning.

Findings

Multiple mechanisms together enhance continual learning.

Biologically inspired architecture reduces catastrophic forgetting.

Dendritic structures improve context-dependent processing.

Abstract

Humans excel at continually acquiring, consolidating, and retaining information from an ever-changing environment, whereas artificial neural networks (ANNs) exhibit catastrophic forgetting. There are considerable differences in the complexity of synapses, the processing of information, and the learning mechanisms in biological neural networks and their artificial counterparts, which may explain the mismatch in performance. We consider a biologically plausible framework that constitutes separate populations of exclusively excitatory and inhibitory neurons that adhere to Dale's principle, and the excitatory pyramidal neurons are augmented with dendritic-like structures for context-dependent processing of stimuli. We then conduct a comprehensive study on the role and interactions of different mechanisms inspired by the brain, including sparse non-overlapping representations, Hebbian learning, synaptic consolidation, and replay of past activations that accompanied the learning event. Our study suggests that the employing of multiple complementary mechanisms in a biologically plausible architecture, similar to the brain, may be effective in enabling continual learning in ANNs.