The Roles of Supervised Machine Learning in Systems Neuroscience

TL;DR

This paper reviews how machine learning has been increasingly used in systems neuroscience, highlighting its roles in solving engineering problems, identifying key variables, benchmarking models, and serving as a brain model.

Contribution

It categorizes the four primary roles of machine learning in systems neuroscience, emphasizing its broad applicability and importance.

Findings

ML aids in solving engineering problems in neuroscience

ML helps identify predictive variables in neural data

ML serves as a benchmark and a model for understanding the brain

Abstract

Over the last several years, the use of machine learning (ML) in neuroscience has been rapidly increasing. Here, we review ML's contributions, both realized and potential, across several areas of systems neuroscience. We describe four primary roles of ML within neuroscience: 1) creating solutions to engineering problems, 2) identifying predictive variables, 3) setting benchmarks for simple models of the brain, and 4) serving itself as a model for the brain. The breadth and ease of its applicability suggests that machine learning should be in the toolbox of most systems neuroscientists.