This is a new introductory mini-course Saul designed this year. Co-directed with Reza Abbasi Asl and Karunesh Ganguly.
Course Description:
Many data analysis 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 models. It has even been proposed as a model of human cognition. This course will survey uses of encoder-decoder models in current neuroscience research. Lectures will be given by UC neuroscientists.
Requirements: proficiency in linear algebra and basic programming is assumed.
Homework will consist of one programming project, group or individual, to be proposed at the end of week 1 of the course and completed by the end of week 3.
The encoder-decoder paradigm encompasses many machine learning endeavors