Biologically-Inspired Spatial Neural Networks

Maciej Wołczyk, Jacek Tabor, Marek Śmieja, Szymon Maszke

TL;DR: Bio-inspired artificial neural networks, consisting of neurons positioned in a two-dimensional space, are capable of forming independent groups for performing different tasks.

Keywords: deep learning, neuroscience, multi-task learning

Abstract: We introduce bio-inspired artificial neural networks consisting of neurons that are additionally characterized by spatial positions. To simulate properties of biological systems we add the costs penalizing long connections and the proximity of neurons in a two-dimensional space. Our experiments show that in the case where the network performs two different tasks, the neurons naturally split into clusters, where each cluster is responsible for processing a different task. This behavior not only corresponds to the biological systems, but also allows for further insight into interpretability or continual learning.