Go to Main Content

Brown University

 

HELP | EXIT

Detailed Course Information

 

Spring 2022
Mar 29, 2024
Transparent Image
  Select the desired Level or Schedule Type to find available classes for the course.

CSCI 2952N - Advanced Topics in Deep Learning
Prepares graduate students with the knowledge they need to apply Deep Learning techniques for their own research. 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 study recent attempts to interpret these models, thus revealing potential risks on model bias. Paper reading, student presentations, and invited guest lectures. Students required to work on a final project that explores a novel direction along the line of the papers we cover.
1.000 Credit hours
1.000 Lecture hours

Levels: Graduate, Undergraduate
Schedule Types: Primary Meeting

Computer Science Department

Restrictions:
Must be enrolled in one of the following Levels:     
      Graduate

Prerequisites:
(Graduate level CSCI 1430 Minimum Grade of S or Graduate level CSCI 1470 Minimum Grade of S) and Graduate level CSCI 1420 Minimum Grade of S

Return to Previous New Search
Transparent Image
Skip to top of page
Release: 8.7.2.4