Learning Bayesian Statistics BITESIZE | Practical Applications of Causal AI with LLMs, with Robert Ness
Jul 30, 2025
Robert Ness, a Microsoft expert in causal assumptions, shares insights on the intersection of causal inference and deep learning. He emphasizes the importance of understanding causal concepts in statistical modeling. The conversation dives into the evolution of probabilistic machine learning and the impact of inductive biases on AI models. Notably, Ness elaborates on how large language models can formalize causal relationships, translating natural language into structured frameworks, making causal analysis more accessible and practical.
AI Snips
Chapters
Transcript
Episode notes
Separate Causal Assumptions From Stats
- Many causal inference resources mix causal ideas with statistical practicalities, which can overwhelm learners.
- Robert Ness focuses on causal assumptions using graphs and lets software handle statistical details.
Go Broad Then Deep in Causality
- Use high-level graphical approaches to grasp causal modeling broadly.
- Deep dive only into needed specialized statistical techniques for your domain.
Overwhelmed Learners Story
- Robert shares a story of a person overwhelmed by theoretical knowledge during interviews.
- This highlights the burden learners face when they think they must master everything immediately.