Advanced Topics in Deep Learning
- Course Home Page:
|Offered this year?||Yes|
|When Offered?||Every year|
This course aims at preparing graduate-level students the research knowledge they need to apply Deep Learning techniques for their own research. Over the past few years, there has been tremendous success in developing unified neural architectures that achieve state-of-the-art performance on language understanding (GPT-3), visual perception (ViT), and even protein structure prediction (AlphaFold). We plan to understand how they work, and how the success of such unified models can give rise to further developments on self-supervised learning, a technique that trains machine learning models without requiring labeled data; and multimodal learning, a technique that utilizes multiple input sources, such as vision, audio, and text. We will also study recent attempts to interpret these models, thus revealing potential risks on model bias. The course is organized as a combination of paper reading, student presentations, and invited guest lectures. It also requires the students to work on a final project that explores a novel direction they choose along the line of the papers we cover.
Prerequisites are (a) Computer Vision or Deep Learning; AND (b) Machine Learning