Machine Learning Street Talk (MLST) cover image

Prof. BERT DE VRIES - ON ACTIVE INFERENCE

Machine Learning Street Talk (MLST)

00:00

Navigating Active Inference and Model Adaptation

This chapter explores the challenges of implementing active inference in large models, highlighting the complexities of multidimensional integrals and the necessity of heuristic methods for approximation. It discusses the importance of adaptability in cognitive processes and the role of communication and language in shaping model flexibility. Furthermore, the conversation delves into the dynamics of model training within the context of evolutionary principles and the intricacies of graph theory in relation to variational algorithms.

Transcript
Play full episode

The AI-powered Podcast Player

Save insights by tapping your headphones, chat with episodes, discover the best highlights - and more!
App store bannerPlay store banner
Get the app