Virtual Poster presentation / poster accept
Sparse Distributed Memory is a Continual Learner
Trenton Bricken · Xander Davies · Deepak Singh · Dmitry Krotov · Gabriel Kreiman
Keywords: [ Neuroscience and Cognitive Science ] [ sparsity ] [ Sparse Distributed Memory ] [ Top-K Activation ] [ Biologically Inspired ] [ continual learning ]
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.