CS 205L:
Continuous Mathematical Methods with an Emphasis on Machine Learning
A survey of numerical approaches to the continuous mathematics with emphasis on machine and deep learning. Although motivated from the standpoint of machine learning, the course will focus on the underlying mathematical methods including computational linear algebra and optimization, as well as special topics related to training/using neural networks including automatic differentiation via backward propagation, steepest/gradient decent, momentum methods and adaptive time stepping for ordinary differential equations, etc. Students have the option of doing written homework and either a takehome or in class exams with no programming required, or may skip the exams and instead do a programming project. (Replaces CS205A, and satisfies all similar requirements.) Prerequisites: Math 51; Math 104 or 113 or equivalent or comfortable with the associated material.
Terms: Win

Units: 3

Grading: Letter or Credit/No Credit