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

Fahad Sarfraz, Elahe Arani, Bahram Zonooz

Keywords: Continual Learning, Catastrophic Forgetting, Brain-inspired Mechanisms, Active Dendrites, Dale's Principle, Hebbian Learning, Sparsity

TL;DR: 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

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 counterpart, which may explain the mismatch in performance. We consider a biologically plausible framework that constitutes separate populations of exclusively excitatory and inhibitory neurons which 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 employing multiple complementary mechanisms in a biologically plausible architecture, similar to the brain, can be effective in enabling continual learning in ANNs.

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.

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: Yes

Please Choose The Closest Area That Your Submission Falls Into: Neuroscience and Cognitive Science (e.g., neural coding, brain-computer interfaces)