Sketching the Power of Machine Learning to Decrypt a Neural Systems Model of Behavior

Abstract

Uncovering brain-behavior mechanisms is the ultimate goal of neuroscience. A formidable amount of discoveries has been made in the past 50 years, but the very essence of brain-behavior mechanisms still escapes us. The recent exploitation of machine learning (ML) tools in neuroscience opens new avenues for illuminating these mechanisms. A key advantage of ML is to enable the treatment of large data, combing highly complex processes. This essay provides a glimpse of how ML tools could test a heuristic neural systems model of motivated behavior, the triadic neural systems model, which was designed to understand behavioral transitions in adolescence. This essay previews analytic strategies, using fictitious examples, to demonstrate the potential power of ML to decrypt the neural networks of motivated behavior, generically and across development. Of note, our intent is not to provide a tutorial for these analyses nor a pipeline. The ultimate objective is to relate, as simply as possible, how complex neuroscience constructs can benefit from ML methods for validation and further discovery. By extension, the present work provides a guide that can serve to query the mechanisms underlying the contributions of prefrontal circuits to emotion regulation. The target audience concerns mainly clinical neuroscientists. As a caveat, this broad approach leaves gaps, for which references to comprehensive publications are provided.

Keywords

• triadic neural systems model
• development
• adolescence
• machine learning
• networks