Sparse Coding in a Dual Memory System for Lifelong Learning

TL;DR

This paper introduces a biologically inspired sparse coding approach combined with a dual memory system in deep neural networks to improve lifelong learning by reducing forgetting and balancing feature reuse.

Contribution

It proposes a novel sparse coding mechanism with a dual memory system that enhances continual learning in neural networks, inspired by neurophysiological processes.

Findings

Reduces catastrophic forgetting in lifelong learning tasks.

Balances feature reuse and interference based on class similarity.

Improves retention of previous knowledge while learning new tasks.

Abstract

Efficient continual learning in humans is enabled by a rich set of neurophysiological mechanisms and interactions between multiple memory systems. The brain efficiently encodes information in non-overlapping sparse codes, which facilitates the learning of new associations faster with controlled interference with previous associations. To mimic sparse coding in DNNs, we enforce activation sparsity along with a dropout mechanism which encourages the model to activate similar units for semantically similar inputs and have less overlap with activation patterns of semantically dissimilar inputs. This provides us with an efficient mechanism for balancing the reusability and interference of features, depending on the similarity of classes across tasks. Furthermore, we employ sparse coding in a multiple-memory replay mechanism. Our method maintains an additional long-term semantic memory that aggregates and consolidates information encoded in the synaptic weights of the working model. Our extensive evaluation and characteristics analysis show that equipped with these biologically inspired mechanisms, the model can further mitigate forgetting.