Learning Bayesian Statistics #137 Causal AI & Generative Models, with Robert Ness
8 snips
Jul 23, 2025 Robert Ness, a research scientist at Microsoft and faculty at Northeastern University, dives deep into Causal AI. He discusses the critical role of causal assumptions in statistical modeling and how they enhance decision-making processes. The integration of deep learning with causal models is explored, revealing new frontiers in AI. Furthermore, Ness emphasizes the necessity of statistical rigor when evaluating large language models and highlights practical applications and future directions for causal generative modeling in various fields.
AI Snips
Chapters
Books
Transcript
Episode notes
From Tibet Fieldwork to Stats
- Robert Ness started in economics but shifted to statistics after fieldwork in Tibet involving cordyceps mushrooms.
- His diverse background brings a unique perspective often missing from hyper-optimized AI career paths.
Marrying Graphs and Deep Learning
- Graphical causality and deep learning integration allow explicit causal assumptions within black-box models.
- This marriage leverages causal DAGs and deep learning inference, enhancing AI interpretability and rigor.
Practical Causal Learning Strategy
- Focus causal inference learning on understanding causal assumptions first via graphical models.
- Rely on existing statistical libraries to handle statistical complexities, unburdening you from technical overload.
