The roles of supervised machine learning in systems neuroscience

Area of Science:

• Systems Neuroscience
• Computational Neuroscience
• Machine Learning Applications

Background:

• Rapid growth in machine learning (ML) adoption within neuroscience research.
• Need for a comprehensive overview of ML's current and future impact on systems neuroscience.

Purpose of the Study:

• To review the realized and potential contributions of machine learning (ML) in systems neuroscience.
• To delineate the key roles ML plays in advancing neuroscience research.

Main Methods:

• Literature review of machine learning applications in systems neuroscience.
• Categorization of ML's roles into four primary functions.

Main Results:

• Identified four key roles for ML: engineering solutions, identifying predictive variables, benchmarking brain models, and serving as a model for the brain.
• Demonstrated the broad applicability and utility of ML tools for neuroscientists.

Conclusions:

• Machine learning (ML) offers significant value across diverse areas of systems neuroscience.
• ML should be considered an essential tool for systems neuroscientists due to its versatility and impact.