Neural Networks Compositionality Debate
Raphaël discusses the empirical claim that neural networks lack compositional behavior seen in humans, highlighting recent progress in deep learning. He explores the debate on achieving compositional behavior and the mechanisms supporting it in human cognition.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#107 - Dr. RAPHAËL MILLIÈRE - Linguistics, Theory of Mind, Grounding
Related Questions
How does the architecture of neural networks relate to their ability to reason in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Neural Networks and Reasoning?
How does the architecture of neural networks relate to their ability to reason in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Neural Networks and Reasoning?
How does the architecture of neural networks relate to their ability to reason in the episode Ilya Sutskever: Deep Learning | Lex Fridman Podcast #94 and the clip Neural Networks and Reasoning?