AI for Neuroscience: Animal Behavior Phenotyping and Modeling Neurological Disorders

Our team is developing deep learning models for animal behavior phenotyping for preclinical research associated with neurological disorders (Alzheimer’s, autism, depression). Our team is collaborating with the UF Neuroscience Department in pursuit of this work.

UF Informatics Institute Seed Fund Focus on AI grant (competition): “Phenotyping an Animal Model of Major Depressive Disorder: A Deep-Learning Approach.”, 2021. UF Research, Artificial Intelligence Research Catalyst Fund award (HiperGator resources for one year): “A Deep-Learning Approach to Phenotype a Rodent Model of Major Depressive Disorder.”, 2020

We present an overview of human action recognition and pose estimation methods that are based on convolutional neural network (CNN) architectures and have been adapted for animal behavior classification in neuroscience. Pose estimation, estimating joint positions from an image frame, is included because it is often applied before classifying animal behavior.