This course introduces core concepts in computer vision, with a focus on generative models for images and videos. This course covers foundational strategies for classifying visual data like SVMs and Fourier Transforms then explores multimodal strategies for combining text and images such as CLIP, culminating in generating images using Diffusion Models. Prereq: MATH 129 and MATH 166 and CSCI 425. Dual-listing: CSCI 623.