Use of deep learning tools for tracking mouse behavior to understand effects of movement and arousal state on neural activity in somatosensory cortex
Dan Feldman, Professor
Molecular and Cell Biology
Closed. This professor is continuing with Fall 2023 apprentices on this project; no new apprentices needed for Spring 2024.
This project aims to investigate the effects of body movements and arousal state on behavioral performance accuracy, and on neural activity in specific cell classes during goal-directed behavior in mice.
Role: Students will apply the DeepLabCut algorithm (Mathis et al., 2018) to train and optimize deep neural networks which will then be used to track body movements and perform pupillometry in novel videos of behaving mice. They will learn to read primary research papers and review articles, and to synthesize information from these sources to develop and improve methods for behavioral video analysis in the lab. Students will periodically present their progress on the project and will create documentation of methods for future users. Contributions to the advancement of the project will lead to inclusion as an author on resulting conference abstracts and publications.
Qualifications: Students should have coding experience (Matlab and/or Python) and an interest in applying coding skills to analyze movies of mouse behavior. Should maintain a regular work schedule, be proactive at problem-solving, and maintain clear communication with the supervisor and team about the project.
Day-to-day supervisor for this project: Deepa Ramamurthy, Post-Doc
Hours: 9-11 hrs
Off-Campus Research Site: Project can be fully remote, with the option to work in-person.
Related website: https://www.feldmanlab.org/
Biological & Health Sciences