By NSF TILOS6 October 2023 TILOS Fireside Chat: Theory in the Age of Modern AI A conversation about theory in the age of modern artificial intelligence (AI) with TILOS member panelists Nisheeth Vishnoi, Tara Javidi, Misha Belkin, and Arya Mazumdar (moderator). 235views Foundations,Panel Discussions You may also like 01:01:02 TILOS Seminar: Synthetic Tasks as Testbeds for Attributing Model Behavior 279views Foundations,TILOS Seminar Series deep learning,learning theory,machine learning,neural networks,synthetic tasks 01:03:55 TILOS Seminar: Unlearnable Facts Cause Hallucinations in Pretrained Language Models 309views Foundations,Machine Learning,TILOS Seminar Series hallucinations,machine learning,natural language processing,pretrained LMs 00:47:35 TILOS Seminar: How Transformers Learn Causal Structure with Gradient Descent 380views Foundations,Machine Learning,TILOS Seminar Series causal inference,machine learning,transformers 01:11:07 TILOS Seminar: Off-the-shelf Algorithmic Stability 303views Foundations,Machine Learning,TILOS Seminar Series algorithmic stability,machine learning 01:04:58 TILOS Seminar: What Kinds of Functions do Neural Networks Learn? Theory and Practical Applications 296views Foundations,Machine Learning,TILOS Seminar Series machine learning,multi-task learning,neural networks,single-task learning 55:35 TILOS Seminar: Transformers Learn In-context by (Functional) Gradient Descent 313views Foundations,Machine Learning,TILOS Seminar Series in-context learning,machine learning architectures,neural networks,transformers 59:25 TILOS Seminar: How Large Models of Language and Vision Help Agents to Learn to Behave 315views Foundations,Machine Learning,TILOS Seminar Series foundation models,vision models,vision-language models 01:04:33 TILOS Webinar: AI Ethics in Research 148views AI Ethics,Panel Discussions bias,fairness 55:02 TILOS Seminar: The Dissimilarity Dimension: Sharper Bounds for Optimistic Algorithms 274views Foundations,TILOS Seminar Series bandits,Eluder dimension,optimistic algorithms,reinforcement learning 56:45 TILOS Seminar: Building Personalized Decision Models with Federated Human Preferences 319views Foundations,TILOS Seminar Series dueling bandits,federated learning «12345»Page 3 of 5
