Sparse Distributed Memory is a Continual Learner
This work addresses the continual learning problem for artificial neural networks, offering a novel approach that is incremental in its adaptation of existing methods.
The paper tackled the problem of continual learning in artificial neural networks by creating a modified Multi-Layered Perceptron (MLP) based on Sparse Distributed Memory (SDM) and biological insights, resulting in a strong continual learner that requires no memory replay or task information.
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.