Cell-type Neural Ordinary Differential Equation Models for Parsing Biologically-Constrained Contributions to Neural Dynamics

William C Surmeier, Bareesh Bhaduri, Jiyul Kim, Diya Basrai, Andrew Miri, Joshua I Glaser

Keywords: Neuroscience, Dynamical System, Neural ODE, Biological Constraints

TL;DR: Cell-Type NODE (CT-NODE) models break down neural dynamics by cell population, incorporating biological constraints to reveal how excitatory and inhibitory populations interact, offering better accuracy and interpretability than standard NODE models.

Abstract:

Understanding how populations of individual neurons interact to shape the overall dynamics of neural activity is a central question in computational and systems neuroscience. Recent work has shown that neural ordinary differential equation (NODE) models are able to model neural activity dynamics with high accuracy and interpretability of the underlying dynamics. However, existing NODE models treat all neurons as part of a homogenous group, preventing
understanding how underlying neural populations (e.g. cell types) contribute to the overall dynamics. Here, we introduce Cell-Type NODE (CT-NODE) models. These models A) decompose the overall dynamics into components specific to each population, allowing understanding each population's interactions with one another; and B) provide biological constraints on the contributions of excitatory and inhibitory populations towards the dynamics, using a variant of monotonic neural networks. Using both synthetic and recorded neural activity data during a naturalistic climbing task, we show that CT-NODE models can provide equivalent, or greater, accuracy of dynamics modeling compared to standard NODE models, while enabling a newfound biologically-constrained understanding of neural populations’ interactions and roles in the underlying dynamics.

Primary Area: applications to neuroscience & cognitive science

Submission Number: 15377