Shaping dynamical neural computations using spatiotemporal constraints

Abstract

Dynamics play a critical role in computation. The principled evolution of states over time enables both biological and artificial networks to represent and integrate information to make decisions. In the past few decades, significant multidisciplinary progress has been made in bridging the gap between how we understand biological versus artificial computation, including how insights gained from one can translate to the other. Research has revealed that neurobiology is a key determinant of brain network architecture, which gives rise to spatiotemporally constrained patterns of activity that underlie computation. Here, we discuss how neural systems use dynamics for computation, and claim that the biological constraints that shape brain networks may be leveraged to improve the implementation of artificial neural networks. To formalize this discussion, we consider a natural artificial analog of the brain that has been used extensively to model neural computation: the recurrent neural network (RNN). In both the brain and the RNN, we emphasize the common computational substrate atop which dynamics occur -- the connectivity between neurons -- and we explore the unique computational advantages offered by biophysical constraints such as resource efficiency, spatial embedding, and neurodevelopment.

arXiv comment7 figures, 18 pages

References in corpus (6)

• Recent Advances in Physical Reservoir Computing: A Review
• Linking connectivity, dynamics and computations in low-rank recurrent neural networks
• Recurrent Network Models Of Sequence Generation And Memory
• Generative models of the human connectome
• Models of communication and control for brain networks: distinctions, convergence, and future outlook
• Learning Continuous Chaotic Attractors with a Reservoir Computer