Shuhei J. Yamazaki

DiverScan is a deep-learning framework that uses attention mechanisms to analyze animal behavior data, identifying condition-specific features across diverse experiments.

This study identifies how prior experience modulates sensory gain control in C. elegans ASH neurons, altering their response to odor concentration changes and enhancing odor avoidance behavior.

This paper introduces a hybrid machine learning method to estimate behavioral states and extract features from low-content animal trajectory data, validated across diverse species and environments.