Machine Learning Street Talk (MLST)

Dr. Sanjeev Namjoshi - Active Inference

46 snips
Oct 22, 2024
Dr. Sanjeev Namjoshi, a machine learning engineer and author of a book on Active Inference, dives into its theoretical and practical aspects. He explains how Active Inference utilizes the Free Energy Principle to minimize uncertainty in biological and artificial systems. Namjoshi highlights its potential to revolutionize machine learning, akin to deep learning's early days. He contrasts it with traditional methods, emphasizing its ability to foster exploration and curiosity, and explores the complexities of agency in AI and its implications for future cognitive modeling.
Ask episode
AI Snips
Chapters
Books
Transcript
Episode notes
INSIGHT

Self-Organization and Persistence

  • Self-organization can create persistent systems through interactions and feedback loops.
  • Autocatalytic loops, enclosures, and resource exchange can maintain system boundaries.
INSIGHT

AI Agency: A Modeling Choice

  • The question of AI agency is a complex philosophical debate.
  • The utility of agential language depends on whether it accurately predicts system behavior.
INSIGHT

Ethics and Information Technology

  • Existing legal and ethical frameworks struggle with information realm technologies.
  • AI chatbots present an ethical challenge as they mimic human behavior without legal accountability.
Get the Snipd Podcast app to discover more snips from this episode
Get the app