Deep Unsupervised Learning | UC Berkeley Spring 2024

Explore cutting-edge deep learning techniques in generative models and self-supervised learning. Taught by renowned instructors at UC Berkeley.

Introduction

This course will cover two areas of deep learning in which labeled data is not required: Deep Generative Models and Self-Supervised Learning. Recent advances in generative models have made it possible to realistically model high-dimensional raw data such as natural images, audio waveforms and text corpora. Strides in self-supervised learning have started to close the gap between supervised representation learning and unsupervised representation learning in terms of fine-tuning to unseen tasks.

Highlights

• Covers the theoretical foundations of deep generative models and self-supervised learning
• Newly enabled applications of these cutting-edge deep learning techniques
• Taught by a team of renowned instructors from UC Berkeley

Recommendation

This course is targeted towards a PhD level audience, but exceptional undergraduates could also be a good fit. It is a real course with substantial homework, a midterm, and a final project. Students interested in getting a head start can refer to the previous offering of the course.