Theoretical Foundations of Modern Machine Learning Paradigms
38:15Foundations, Privacy & Generalization Challenges in Modern Machine Learning
36:41Efficient Algorithms for Reliable Machine Learning
37:26Computational Thinking on Learning Models
38:30On the Komlós Conjecture
33:41Multi-objective Learning: An Algorithmic Toolbox for Optimal Predictions Anytime Anywhere!
37:40Approximately Packing Dijoins Via Nowhere-Zero Flows
33:46Lightning Talks!
56:01Venturing out into the world with AI
44:41Unfamiliar Terrain
29:51Astral Space: Convex Analysis at Infinity
44:01AI and Safety
29:26The Role of TCS in Understanding (AI) Consciousness
43:21The Conscious Turing Machine (CTM), a formally defined Theoretical model of Consciousness
45:00Theory of Modern AI: Learning Theoretic, Game Theoretic, and Algorithmic Perspectives
40:41An Occam's Razor Principle for Transformers?
39:55Red Points and Blue Points
38:15Latent Variable models and Subset Smoothing
29:26Enhanced and Efficient Reasoning in Large Language Models
36:16Theory of Modern AI: Learning Theoretic, Game Theoretic, and Algorithmic Perspectives
Nina Balcan explores the multifaceted theoretical underpinnings of modern AI, integrating learning theoretic, game theoretic, and algorithmic perspectives to explain AI's capabilities and limitations.
Nina Balcan (Carnegie Mellon University)
The Role of TCS in Modern Machine Learning
The Conscious Turing Machine (CTM), a formally defined Theoretical model of Consciousness
Next · Lecture 16An Occam's Razor Principle for Transformers?