Weakly Supervised Causal Representation Learning
Offered By: Valence Labs via YouTube
Course Description
Overview
Explore weakly supervised causal representation learning in this comprehensive talk by Johann Brehmer from Valence Labs. Delve into the challenges of learning high-level causal variables and structures from unstructured, low-level data like pixel-level information. Discover how weak supervision, involving paired samples before and after random interventions, enables learning causal variables and structures. Examine implicit latent causal models and variational autoencoders that represent causal structure without explicit graph optimization. Learn about the application of these models to simple image data for disentangling causal variables and enabling causal reasoning. Gain insights into the current limitations of causal representation learning and potential future developments. The talk covers key topics including structural causal models, theoretical foundations, practical implementations, experimental results, and concludes with an outlook on the field and a discussion session.
Syllabus
- Discussant Slide
- Introduction and Background
- Structural Causal Models
- Theory
- Assumptions
- Practice
- Experiments
- Outlook
- Discussion
Taught by
Valence Labs
Related Courses
Facebook: Product Optimization with Adaptive Experimentation - F8 2019Meta via YouTube Improving Conversational AI - Advancements in NLP Research at Facebook
Meta via YouTube SILCO: Show a Few Images, Localize the Common Object
University of Central Florida via YouTube Open AI's Whisper Is Amazing
sentdex via YouTube Annotation-Efficient Object Detection: Unsupervised Discovery to Active Learning
VinAI via YouTube