The Geometry of Reasoning and Learning in the Age of Agentic AI with Stefano Soatto
From University of California Audio Podcasts (Audio) by UCTV
May 6, 2026 · 44 min
About this episode
Stefano Soatto discusses the impact of artificial intelligence on understanding machine learning systems through the lens of information geometry.
Artificial intelligence affects how we understand the behavior of machine learning systems. Stefano Soatto, VP of Applied Science, Amazon Web Services, explains how ideas from information geometry shape emerging theories of how these artifacts work. Soatto examines the natural gradient, the connections between geometry and concepts such as probability distributions, entropy, mutual information, and KL divergence, and the challenge of defining information in trained models, helping clarify how reasoning and learning can be understood in the era of AI. Series: "Kyoto Prize Symposium" [Science] [Show ID: 41494]
People in this episode
Guest: Stefano Soatto
Topics covered
- artificial intelligence
- machine learning
- information geometry
- reasoning
- learning
- probability distributions
Keywords
- AI
- machine learning
- information geometry
- natural gradient
- entropy
- mutual information
- KL divergence
Mentioned in this episode
Organizations: Amazon Web Services
Books & works: Kyoto Prize Symposium
More episodes of University of California Audio Podcasts (Audio)
- Ethical Sourcing in Health Data Supply Chains: Considerations for ML/AI Training · June 8, 2026 · 24 min
- Prostate Cancer: Radiation Therapy for Local Recurrence · June 7, 2026 · 11 min
- Stem-Cell Aging and Pathways to Precancer Evolution · June 5, 2026 · 22 min
- Targeted Therapies for Prostate Cancer · June 4, 2026 · 12 min
- Prostate Cancer: PSMA PET and Functional Imaging · June 4, 2026 · 16 min
- Prostate Cancer Immunotherapy · June 3, 2026 · 11 min
Explore listener stats, chart rankings, contacts and more on the University of California Audio Podcasts (Audio) podcast page.