The Roles of Supervised Machine Learning in Systems Neuroscience
It provides a framework for neuroscientists to understand and apply ML, but it is a review paper, so it is incremental in synthesizing existing knowledge.
The paper reviews the roles of supervised machine learning in systems neuroscience, identifying four primary contributions such as solving engineering problems and serving as brain models, and concludes that ML should be widely adopted by neuroscientists.
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.