Published Jul 11, 2024

David Pfau: Manifold Factorization and AI for Science

David Pfau from Google DeepMind delves into the synergy of AI and quantum mechanics, unveiling how machine learning can tackle computational physics challenges, alongside innovative frameworks like Geomancer for manifold learning and spectral learning techniques to optimize and understand complex data structures.

Episode Highlights

Topics covered

Episode Highlights

Related Episodes

Hugo Larochelle: Deep Learning as Science
Answers 383 questions
Luis Voloch: AI and Biology
Answers 383 questions
Michael Levin & Adam Goldstein: Intelligence and its Many Scales
Answers 383 questions
François Chollet: Keras and Measures of Intelligence
Answers 383 questions
Kyunghyun Cho: Neural Machine Translation, Language, and Doing Good Science
Answers 383 questions
Thomas Dietterich: From the Foundations
Answers 383 questions
Ben Wellington: ML for Finance and Storytelling through Data
Answers 383 questions
Yoshua Bengio: The Past, Present, and Future of Deep Learning
Answers 383 questions
Yann LeCun on his Start in Research and Self-Supervised Learning
Answers 383 questions
Peter Lee: Computing Theory and Practice, and GPT-4's Impact
Answers 383 questions
David Chalmers on AI and Consciousness
Answers 383 questions
Max Woolf: Data Science at BuzzFeed and AI Content Generation
Answers 383 questions
Catherine Olsson and Nelson Elhage: Anthropic, Understanding Transformers
Answers 383 questions
Sebastian Raschka: AI Education and Research
Answers 383 questions
Joel Lehman: Open-Endedness and Evolution through Large Models
Answers 383 questions

Dexa/Daniel Bashir

David Pfau: Manifold Factorization and AI for Science

Topics covered

Popular Clips

Grand Ideas, Spectral Networks

Uncovering Missing Insights

Infinite Automata Method

Hardware Evolution

Learning Representations, Data Augmentation

Self-Generative Learning

Scaling Methods

Brain-inspired AI

Manifold Learning Insights

Uncovering Disentangled Features

Balancing Aspirations

Modeling Data Growth

Mathematical Connections

Gradient Descent Insights

Manifold Decomposition

Episode Highlights

AI and Scientific Research

Manifold Learning

Spectral Learning

Related Episodes

Hugo Larochelle: Deep Learning as Science

Luis Voloch: AI and Biology

Michael Levin & Adam Goldstein: Intelligence and its Many Scales

François Chollet: Keras and Measures of Intelligence

Kyunghyun Cho: Neural Machine Translation, Language, and Doing Good Science

Thomas Dietterich: From the Foundations

Ben Wellington: ML for Finance and Storytelling through Data

Yoshua Bengio: The Past, Present, and Future of Deep Learning

Yann LeCun on his Start in Research and Self-Supervised Learning

Peter Lee: Computing Theory and Practice, and GPT-4's Impact

David Chalmers on AI and Consciousness

Max Woolf: Data Science at BuzzFeed and AI Content Generation

Catherine Olsson and Nelson Elhage: Anthropic, Understanding Transformers

Sebastian Raschka: AI Education and Research

Joel Lehman: Open-Endedness and Evolution through Large Models

David Pfau: Manifold Factorization and AI for Science

Topics covered

Popular Clips

Episode Highlights

AI and Scientific Research

Manifold LearningDavid Pfau explores the innovative Geomancer framework, highlighting its potential in manifold learning and metric recovery. He discusses its theoretical foundations, practical applications, and the challenges of decomposing complex data structures.

Manifold Learning

Spectral LearningDavid Pfau explores the intricacies of spectral learning methodologies and their applications in machine learning and physics. He discusses the challenges of optimization and the elegance of mathematical connections in these fields.

Spectral Learning

Related Episodes