Published Feb 16, 2023
Hattie Zhou: Lottery Tickets and Algorithmic Reasoning in LLMs
Hattie Zhou delves into the transformative power of forgetfulness in neural networks, efficient model training through the Lottery Ticket Hypothesis, and how language models harness in-context learning to tackle complex tasks, offering a glimpse into the future of AI and algorithmic reasoning.
Topics covered
Popular Clips
Questions from this episode
- Asked by 38 people
Episode Highlights
Related Episodes
Jonathan Frankle: From Lottery Tickets to LLMs
Answers 383 questions
Zachary Lipton: Where Machine Learning Falls Short
Answers 383 questions
Hugo Larochelle: Deep Learning as Science
Answers 383 questions
Kyunghyun Cho: Neural Machine Translation, Language, and Doing Good Science
Answers 383 questions
Vera Liao: AI Explainability and Transparency
Answers 383 questions
Joel Lehman: Open-Endedness and Evolution through Large Models
Answers 383 questions
Subbarao Kambhampati: Planning, Reasoning, and Interpretability in the Age of LLMs
Answers 383 questions
Sara Hooker: Cohere For AI, the Hardware Lottery, and DL Tradeoffs
Answers 383 questions
Been Kim: Interpretable Machine Learning
Answers 383 questions
Thomas Dietterich: From the Foundations
Answers 383 questions
Melanie Mitchell: Abstraction and Analogy in AI
Answers 383 questions
Greg Yang on Communicating Research, Tensor Programs, and µTransfer
Answers 383 questions
Chip Huyen: Machine Learning Tools and Systems
Answers 383 questions
Eric Jang on Robots Learning at Google and Generalization via Language
Answers 383 questions
Seth Lazar: Normative Philosophy of Computing
Answers 383 questions