The Transformative Ideas Podcast podcast

#30: Language Models, Active Inference and Latent Variables with Alejandro Daniel Noel

0:00
1:42:30
Manda indietro di 15 secondi
Manda avanti di 15 secondi

In this episode, our host Manuel Brenner is joined by Alejandro Daniel Noel. Alejandro got his masters from TU Delft working with Acitive Inference and the Free Energy Principle, and is now a full time software engineer at Google in Zürich, specializing on machine learning engineering of language models for conversational AI.

We discuss the free energy principle, active inference, the role of uncertainty, latent variable models, language and tokenization, causality, diffusion models, DALL-E, paths towards AGI, JEPA, language and consciousness, attention, self-attention, and many more topics.

Stay tuned for more episodes: https://mailchi.mp/0346443b6ddf/acit-global-signup

Altri episodi di "The Transformative Ideas Podcast"