Module: 2
Sponsoring Program: Neuroscience
Administrator: Lucita Nacionales
STUDY LIST INFORMATION
Course Number: NS 219
Course Name: Special Topics in Basic and Translational Neuroscience (Encoder-Decoder Models)
Units: 3
Grading Option: S/U
Course Director: Saul Kato
Co-director: Christoph Kirst
MORE COURSE INFORMATION
Dates: Monday, April 20 - Friday, May 8, 2026
Campus: MB
Location: TBD
Schedule: M,W,F, 9:30am-11:30am
Minimum Class Size: 12
Maximum Class Size: 16
Many machine learning approaches can be thought of as a process of encoding high-dimensional data items into a low-dimensional space, then (optionally) decoding them back into a high-dimensional data space. This paradigm encompasses the endeavors of dimensionality reduction, feature learning, classification, and of particular recent excitement, generative AI models. It has even been proposed as a general model of human cognition. This course will provide a conceptual understanding of the encoder-decoder paradigm and survey uses of encoder-decoder models in current neuroscience research. Lectures will be given by UCSF and other neuroscientists or machine learning practitioners. Each student is expected to complete a small encoder-decoder analysis project using actual data. In-class project time will be provided.