Persistent learning signals and working memory without continuous attractors

TL;DR

This paper introduces a novel understanding of neural attractors, highlighting the role of quasi-periodic attractors in supporting long-term temporal learning and working memory without the need for continuous attractors, with implications for artificial and biological systems.

Contribution

The study reveals that quasi-periodic attractors can support long-term temporal learning, offering a new approach to neural working memory beyond traditional continuous attractors.

Findings

Quasi-periodic attractors enable learning of long temporal relationships.

A new initialization scheme improves RNN performance on temporal tasks.

A robust recurrent memory mechanism for head direction is proposed.

Abstract

Neural dynamical systems with stable attractor structures, such as point attractors and continuous attractors, are hypothesized to underlie meaningful temporal behavior that requires working memory. However, working memory may not support useful learning signals necessary to adapt to changes in the temporal structure of the environment. We show that in addition to the continuous attractors that are widely implicated, periodic and quasi-periodic attractors can also support learning arbitrarily long temporal relationships. Unlike the continuous attractors that suffer from the fine-tuning problem, the less explored quasi-periodic attractors are uniquely qualified for learning to produce temporally structured behavior. Our theory has broad implications for the design of artificial learning systems and makes predictions about observable signatures of biological neural dynamics that can support temporal dependence learning and working memory. Based on our theory, we developed a new initialization scheme for artificial recurrent neural networks that outperforms standard methods for tasks that require learning temporal dynamics. Moreover, we propose a robust recurrent memory mechanism for integrating and maintaining head direction without a ring attractor.