Brain Inspired BI 219 Xaq Pitkow: Principles and Constraints of Cognition
5 snips
Aug 27, 2025 Xaq Pitkow, director of the Lab for the Algorithmic Brain at Carnegie Mellon University, dives into the principles of cognition and their applications. He shares insights on 'inverse rational control,' illustrating how organisms tackle tasks using strategies that often diverge from optimal solutions. The conversation covers the role of probabilistic graph networks in brain computations and introduces a new ecological neuroscience project with collaborative efforts. Xaq emphasizes the intersection of neuroscience and AI, advocating for a diverse range of models to understand cognitive processes.
AI Snips
Chapters
Transcript
Episode notes
Co-Design Experiments With Experimentalists
- Co-design experiments with experimentalists to match theoretical questions and constraints.
- Build collaborations where PI-level vision guides practical experimental trade-offs.
Graphs Provide Powerful Inductive Biases
- Probabilistic graphical models capture causal structure and sparsity that make inference tractable.
- Learning graph structure gives strong inductive bias and enables generalization across contexts.
Rounded Tetrahedron Visualization
- Xaq 3D-printed a rounded tetrahedron to visualize changing graph interactions.
- He uses tangible models to explore probabilistic graph structure and gating.