The course that this site is adapted from, UC Berkeley CS 198-126, is an introductory Computer Vision course for college students. The goal of this site is to adapt a college-level course to be understandable to middle to hgih school students who are interested in taking a look at what computer vision and machine learning in general are like, so a lot of the explanations, math, and vocabulary are heavily simplified. Nonetheless, the content still requires some level of abstract thought and benefits from a basic understanding of knowledge that machine learning is based on, such as linear algebra and multivariable calculus. Still, I have done my best to explain the overarching concepts in a way that is accessible to everyone. If you don’t understand the specifics, that’s okay!

The structure of the course is outlined here. It is divided into six clusters, which are generally grouped by topic and focus, and are also ordered roughly by complexity and currentness. Each lecture corresponds to a video lecture from the Berkeley course. If you have feedback, corrections, or questions about a specific lecture, open an issue!

Further Reading