Universal computation using localized limit-cycle attractors in neural networks

TL;DR

This paper demonstrates that localized limit-cycle attractors in neural networks can be harnessed to perform universal computation by creating and controlling Boolean gates through collision-based interactions of propagating activity patterns.

Contribution

The authors introduce a rewiring algorithm that enables universal Boolean gates in a 2D threshold network using localized attractors and collision-based computing, a novel approach in neural network computation.

Findings

Localized attractors can be used for computation in neural networks.

Collision-based interactions of activity patterns implement Boolean gates.

The approach demonstrates the potential for universal computation in biologically inspired networks.

Abstract

Neural networks are dynamical systems that compute with their dynamics. One example is the Hopfield model, forming an associative memory which stores patterns as global attractors of the network dynamics. From studies of dynamical networks it is well known that localized attractors also exist. Yet, they have not been used in computing paradigms. Here we show that interacting localized attractors in threshold networks can result in universal computation. We develop a rewiring algorithm that builds universal Boolean gates in a biologically inspired two-dimensional threshold network with randomly placed and connected nodes using collision-based computing. We aim at demonstrating the computational capabilities and the ability to control local limit cycle attractors in such networks by creating simple Boolean gates by means of these local activations. The gates use glider guns, i.e., localized activity that periodically generates "gliders" of activity that propagate through space. Several such gliders are made to collide, and the result of their interaction is used as the output of a Boolean gate. We show that these gates can be used to build a universal computer.