Completed
Solution #1: Train a Network to Approximate the Probability Mass Function
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
Understanding Text Generation Through Diffusion Models - From Theory to Implementation
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Modeling Probability Distributions for Generative AI
- 3 Problem #1: No Black Box
- 4 Solution #1: Train a Network to Approximate the Probability Mass Function
- 5 Problem #2: The Normalizing Constant, Z_theta, is Intractable
- 6 Solution #2: Autoregressive Modeling
- 7 Solution #3 Real Solution: Model Score, Not Probability Mass
- 8 Learning the Concrete Score Through Diffusion
- 9 Evaluation
- 10 So What?
- 11 Takeaways
