teaching
Computer Vision
Computer vision seeks to answer a deceptively simple question: how can we build machines that see? This course follows the journey from image formation and representation through filtering, features, motion, depth, and 3D reconstruction, ultimately arriving at visual recognition and understanding.
Deep Learning in Computer Vision
Deep learning powers modern AI systems, from image recognition and generative models to autonomous vehicles and large language models. Through visual intuition, mathematical foundations, and practical examples, you'll develop a deep understanding of neural networks and the ideas behind today's AI systems. By the end of the course, you'll be able to implement deep learning models, understand contemporary research, and continue learning independently.