Universal computation using localized limit-cycle attractors in neural networks
This work addresses the challenge of expanding computing paradigms in neural networks beyond global attractors, potentially benefiting fields like neuromorphic computing and dynamical systems theory, though it appears incremental as it builds on known localized attractor concepts.
The authors tackled the problem of enabling universal computation in neural networks by using localized limit-cycle attractors, demonstrating that interacting localized attractors in threshold networks can implement universal Boolean gates and build a universal computer.
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.