Published Jun 24, 2022
Preetum Nakkiran: An Empirical Theory of Deep Learning
Preetum Nakkiran delves into the empirical theory of deep learning, offering a unique perspective on model behavior through concepts like distributional generalization and the double descent phenomenon, while sharing his personal research journey and emphasizing the importance of blending theoretical and empirical approaches to unravel AI's complexities.
Topics covered
Popular Clips
Episode Highlights
Related Episodes
Hugo Larochelle: Deep Learning as Science
Answers 383 questions
Kyunghyun Cho: Neural Machine Translation, Language, and Doing Good Science
Answers 383 questions
Yoshua Bengio: The Past, Present, and Future of Deep Learning
Answers 383 questions
Percy Liang on Machine Learning Robustness, Foundation Models, and Reproducibility
Answers 383 questions
Anant Agarwal: AI for Education
Answers 383 questions
Vivek Natarajan: Towards Biomedical AI
Answers 383 questions
Yann LeCun on his Start in Research and Self-Supervised Learning
Answers 383 questions
Soumith Chintala: PyTorch
Answers 383 questions
Eric Jang on Robots Learning at Google and Generalization via Language
Answers 383 questions
Peter Lee: Computing Theory and Practice, and GPT-4's Impact
Answers 383 questions
Thomas Dietterich: From the Foundations
Answers 383 questions
Christopher Manning: Linguistics and the Development of NLP
Answers 383 questions
Sasha Rush: Building Better NLP Systems
Answers 383 questions
Sebastian Raschka: AI Education and Research
Answers 383 questions
François Chollet: Keras and Measures of Intelligence
Answers 383 questions