Prereqs: (7.05 and (6.0002 or 6.01)) or permission of instructor
Instructor: Professor Manolis Kellis (email@example.com)
Schedule: TR1-2:30, virtual instruction
Presents innovative approaches to computational problems in the life sciences, focusing on deep learning-based approaches with comparisons to conventional methods. Topics include protein-DNA interaction, chromatin accessibility, regulatory variant interpretation, medical image understanding, medical record understanding, therapeutic design, and experiment design (the choice and interpretation of interventions). Focuses on machine learning model selection, robustness, and interpretation. Teams complete a multidisciplinary final research project using TensorFlow or other framework. Provides a comprehensive introduction to each life sciences problem, but relies upon students understanding probabilistic problem formulations. Students taking graduate version complete additional assignments.
More information on how this subject will be taught at https://eecs.scripts.mit.edu/eduportal/__How_Courses_Will_Be_Taught_Online_or_Oncampus__/S/2021/#6.802J (6.474)