A noise-driven attractor switching device

TL;DR

This paper introduces a noise-driven attractor switching device using stochastic excitable units, enhancing adaptability in neural systems by leveraging noise for stabilization and switching of attractors, mimicking human visual cortex behaviors.

Contribution

It demonstrates how noise can be used to stabilize and switch attractors in neural models, providing a novel mechanism for adaptability against environmental changes.

Findings

Noise stabilizes attractors in neural systems.

Attractor switching mimics stereopsis and binocular rivalry.

Inhibitory connections enable hysteresis behavior.

Abstract

Problems with artificial neural networks originate from their deterministic nature and inevitable prior learnings, resulting in inadequate adaptability against unpredictable, abrupt environmental change. Here we show that a stochastically excitable threshold unit can be utilized by these systems to partially overcome the environmental change. Using an excitable threshold system, attractors were created that represent quasi-equilibrium states into which a system settles until disrupted by environmental change. Furthermore, noise-driven attractor stabilization and switching were embodied by inhibitory connections. Noise works as a power source to stabilize and switch attractors, and endows the system with hysteresis behavior that resembles that of stereopsis and binocular rivalry in the human visual cortex. A canonical model of the ring network with inhibitory connections composed of class 1 neurons also shows properties that are similar to the simple threshold system.