Self-recovery of memory via generative replay

TL;DR

This paper introduces a novel neural network architecture that enhances generative replay with self-recovery capabilities, inspired by brain offline memory reorganization, leading to improved continual learning performance.

Contribution

The paper proposes an adaptive architecture that enables generative replay to autonomously recover memories, mimicking brain-like offline memory reorganization.

Findings

Demonstrates self-recovery of memories in various continual learning tasks

Achieves improved performance over standard generative replay methods

Shows robustness across multiple environments

Abstract

A remarkable capacity of the brain is its ability to autonomously reorganize memories during offline periods. Memory replay, a mechanism hypothesized to underlie biological offline learning, has inspired offline methods for reducing forgetting in artificial neural networks in continual learning settings. A memory-efficient and neurally-plausible method is generative replay, which achieves state of the art performance on continual learning benchmarks. However, unlike the brain, standard generative replay does not self-reorganize memories when trained offline on its own replay samples. We propose a novel architecture that augments generative replay with an adaptive, brain-like capacity to autonomously recover memories. We demonstrate this capacity of the architecture across several continual learning tasks and environments.