Grounding Neuroscience in Behavioral Changes using Artificial Neural Networks

TL;DR

This paper discusses how artificial neural networks can be used to understand the causal relationship between neural activity changes and behavioral outcomes in neuroscience, leveraging interpretability methods from AI.

Contribution

It proposes using artificial neural networks as models to causally link neural circuit changes to behavioral modifications and suggests applying interpretability techniques to identify neural features responsible for behavior.

Findings

Neural networks can simulate neural-behavioral relationships.

Interpretability methods help identify neural features influencing behavior.

Artificial models facilitate causal testing of neural activity effects.

Abstract

Connecting neural activity to function is a common aim in neuroscience. How to define and conceptualize function, however, can vary. Here I focus on grounding this goal in the specific question of how a given change in behavior is produced by a change in neural circuits or activity. Artificial neural network models offer a particularly fruitful format for tackling such questions because they use neural mechanisms to perform complex transformations and produce appropriate behavior. Therefore, they can be a means of causally testing the extent to which a neural change can be responsible for an experimentally observed behavioral change. Furthermore, because the field of interpretability in artificial intelligence has similar aims, neuroscientists can look to interpretability methods for new ways of identifying neural features that drive performance and behaviors.