Skip to yearly menu bar Skip to main content


Virtual Poster presentation / poster accept

Sparse Distributed Memory is a Continual Learner

Trenton Bricken · Xander Davies · Deepak Singh · Dmitry Krotov · Gabriel Kreiman

Keywords: [ continual learning ] [ Biologically Inspired ] [ Top-K Activation ] [ Sparse Distributed Memory ] [ sparsity ] [ Neuroscience and Cognitive Science ]


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.

Chat is not available.