Sparse Distributed Memory is a Continual Learner
Neural and Evolutionary Computing
2023-03-28 v1 Disordered Systems and Neural Networks
Artificial Intelligence
Machine Learning
Neurons and Cognition
Abstract
Continual learning is a problem for artificial neural networks that their biological counterparts are adept at solving. Building on work using Sparse Distributed Memory (SDM) to connect a core neural circuit with the powerful Transformer model, we create a modified Multi-Layered Perceptron (MLP) that is a strong continual learner. We find that every component of our MLP variant translated from biology is necessary for continual learning. Our solution is also free from any memory replay or task information, and introduces novel methods to train sparse networks that may be broadly applicable.
Cite
@article{arxiv.2303.11934,
title = {Sparse Distributed Memory is a Continual Learner},
author = {Trenton Bricken and Xander Davies and Deepak Singh and Dmitry Krotov and Gabriel Kreiman},
journal= {arXiv preprint arXiv:2303.11934},
year = {2023}
}
Comments
9 Pages. ICLR Acceptance