Computing Under Extreme Connectivity Constraints in Artificial and Biological Neural Networks
Wilten Nicola, University of Calgary
Tuesday March 10, 12-1pm
Zoom Link: https://mcgill.zoom.us/j/87078928687
In Person: 550 Sherbrooke, Room 189
Abstract: Many existing models of computation utilizing recurrent neural networks assume dense, unconstrained initial connectivity, where any pair of neurons may be coupled to generate the rich dynamics needed for learning complex temporal patterns. Inspired by invertebrate circuits that often exhibit ring-like connectivity, we show that computation can occur in ultra-sparse spiking and rate reservoirs that are initially coupled as simple unidirectional rings or other ring structures. In contrast to standard recurrent networks, the total number of network parameters in these ring networks scales only linearly with network size, while still producing rich feature sets. We demonstrate that such networks can successfully reproduce a range of dynamical systems tasks, including oscillations, multi-stable switches, and low-dimensional chaotic attractors. Our findings show that structured spatio-temporal dynamics naturally arising from large ring topologies, often observed in invertebrate circuits, are a sufficient mechanism for learning different types of attractors. This work was conducted with Dr. Afroditi Talidou at the Hotchkiss Brain Institute.