Free courses from frontend to fullstack and AI
MIT Sloan: Lead AI Adoption Across Your Organization — Not Just Pilot It
Overview
Google, IBM & Meta Certificates — All 10,000+ Courses at 40% Off
One annual plan covers every course and certificate on Coursera. 40% off for a limited time.
Get Full Access
Explore a high-level conceptual overview of the Free Energy Principle in neuroscience through this 20-minute educational video from NYU Center for Neural Science researcher Artem Kirsanov. Learn how the brain functions as a prediction machine by building models of the world to anticipate sensory observations. Delve into key concepts including generative and recognition models, the significance of priors, variational inference, and practical applications like understanding optical illusions. Progress through a structured examination of world models, the free energy tradeoff between accuracy and complexity, and how approximate inference shapes our perception. Drawing from established neuroscience research and academic sources, gain insights into this powerful framework that bridges theoretical neuroscience with everyday cognitive experiences, all presented in an accessible, non-mathematical format.
Syllabus
Introduction
Role of world models
Free Energy as tradeoff between accuracy and complexity
Sponsor: Squarespace
Generative Model
Priors
Approximate Inference via Recognition Model
Free Energy balance revisited
Explanation for optical illusion
Review
Taught by
Artem Kirsanov