DR. JEFF BECK - THE BAYESIAN BRAIN
Machine Learning Street Talk (MLST)
Bayesian Reasoning and Active Inference
Bayesian reasoning emphasizes that entities like an electron are labels for mathematical equations, rather than something that physically exists. Active inference in machine learning involves an agent framework where every agent has a model and dynamically interacts with the environment to seek and gather information in an efficient manner. This approach is akin to optimal experimental design and allows agents to pursue the most informative data, resembling the way experiments are designed in a laboratory setting. Implementing active inference into behavior has proven remarkably effective, making it a key concept in modern research.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
