Probing machine-learning classifiers using noise, bubbles, and reverse correlation.
Journal:
Journal of neuroscience methods
Published Date:
Jul 25, 2021
Abstract
BACKGROUND: Many scientific fields now use machine-learning tools to assist with complex classification tasks. In neuroscience, automatic classifiers may be useful to diagnose medical images, monitor electrophysiological signals, or decode perceptual and cognitive states from neural signals. However, such tools often remain black-boxes: they lack interpretability. A lack of interpretability has obvious ethical implications for clinical applications, but it also limits the usefulness of these tools to formulate new theoretical hypotheses.