Machine Learning Street Talk (MLST) Dr. Thomas Parr - Active Inference Book
70 snips
May 1, 2024 
Join Dr. Thomas Parr, a postdoctoral scholar at the Wellcome Centre for Human Neuroimaging, as he delves into the fascinating world of active inference. He explores how living systems resist entropy and navigate their environments through a mathematical framework. Parr discusses the evolution of neural networks and contrasts traditional AI with active inference's potential for deeper world modeling. He also navigates complex topics like agency, consciousness, and the collaborative journey of writing his book on these intricate concepts.
AI Snips
Chapters
Books
Transcript
Episode notes
First Meeting with Friston
- Thomas Parr's first meeting with Karl Friston was nerve-wracking.
- Friston agreed to supervise Parr's PhD without looking at his CV.
Active vs. Passive AI
- ChatGPT excels at simulating conversations but lacks the ability to actively seek information.
- Active inference models, unlike passive AI, can change their world model and seek specific data.
Two Roads to Active Inference
- Active inference has two approaches: a "high road" and a "low road."
- The "high road" starts with physics principles, while the "low road" begins with psychology observations.
