Title | Sparse distributed memory is a continual learner |
Publication Type | Conference Poster |
Year of Publication | 2023 |
Authors | Bricken, T, Davies, X, Singh, D, Krotov, D, Kreiman, G |
Conference Name | International Conference on Learning Representations |
Date Published | 03/2023 |
Place Published | Kigali, Rwanda, Africa |
Keywords | Biologically Inspired, Continual Learning, Sparse Distributed Memory, Sparsity, Top-K Activation |
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. |
URL | https://openreview.net/forum?id=JknGeelZJpHP |
Citation Key | 5254 |
Associated Module:
CBMM Relationship:
- CBMM Funded