The Information Bottleneck EP9: AI in Natural Sciences with Tal Kachman
Oct 13, 2025
Guest Tal Kachman is an Assistant Professor at Radboud University, specializing in the intersection of AI and natural sciences. He discusses the innovative role of self-driving labs in materials discovery and the impact of automation on high-throughput experiments. Tal elaborates on using neural ODEs to analyze chemical processes and recover unknown reaction rates. He also addresses the challenges of integrating physics with AI, emphasizing the significance of data quality and standardization in scientific research.
AI Snips
Chapters
Transcript
Episode notes
Self-Driving Labs Accelerate Discovery
- Self-driving labs combine robotics and AI to enable online scientific discovery with feedback loops.
- Tal Kachman emphasizes automation plus learning components to adapt experiments on the fly.
Dynamics Matter More Than Static Properties
- Modeling dynamical processes (diffusion, chemical kinetics) is central and differs from static property prediction.
- Tal focuses on time-aware models like neural ODEs to capture reaction dynamics and rates.
Neural ODEs Revealed Missing Reaction Rates
- Tal describes a project where neural ODEs overlaid on reaction graphs recovered unknown transition rates from real lab kinetics data.
- The work used measured rate constants and discovered missing transition states via universal approximators.