NEAILGJan 15, 2023

Self-recovery of memory via generative replay

arXiv:2301.06030v14 citationsh-index: 25
Originality Highly original
AI Analysis

This addresses the issue of forgetting in continual learning for AI systems, offering a neurally-plausible and memory-efficient solution.

The paper tackles the problem of artificial neural networks lacking the brain's ability to autonomously reorganize memories during offline periods, proposing a novel architecture that enables generative replay to self-recover memories, achieving state-of-the-art performance on continual learning benchmarks.

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.

Foundations

The foundational work for this paper's niche, ranked by how specifically the neighbourhood builds on it — not by global fame.

Your Notes