Completed
Information Bottleneck & Neural Nets
Class Central Classrooms beta
YouTube videos curated by Class Central.
Classroom Contents
KDD 2020: Physics Inspired Models in Artificial Intelligence
Automatically move to the next video in the Classroom when playback concludes
- 1 Intro
- 2 Terminology
- 3 Motivation: Why Physics & AI?
- 4 Why this Tutorial?
- 5 Tutorial Goals
- 6 Interplay of Physics and Al
- 7 The Four Paradigms
- 8 Theory vs. Data?
- 9 Limitations of the 4th Paradigm
- 10 Cautionary Tale: Problems with Big Data
- 11 Parameters Galore!
- 12 Physics: Tycho Brahe to Kepler to Newton
- 13 A Brief History of Physics & Al
- 14 Generalization in Physics & Al
- 15 Generalization in Neural Nets
- 16 Generalization: Observations
- 17 Computational Complexity, Al & Physics
- 18 Complexity Classes
- 19 3-SAT and Phase Transitions
- 20 Problems: Complexity
- 21 Interpretability & Explainability in Al/ML
- 22 Properties of XAI
- 23 Physics Informed Neural Nets (PINN)
- 24 Physics-guided Neural Network (PGNN)
- 25 Physics & Explainable Al: An Illustration
- 26 Results Summary
- 27 Open Questions in Neural Networks
- 28 Statistical physics theory of Deep Learning?
- 29 Information Bottleneck & Neural Nets
- 30 Information Bottlenecks & Physics
- 31 The Committee Machine