Memory and Reasoning
Yann discusses the essential components for creating systems capable of reasoning, emphasizing the need for a working memory akin to the hippocampus. He highlights the limitations of current transformer models in representing vast knowledge like that found in Wikipedia due to their lack of recurrence. The conversation delves into how iterative processes can enhance knowledge representation and reasoning capabilities.In this clip
From this podcast
Lex Fridman Podcast
Yann LeCun: Deep Learning, ConvNets, and Self-Supervised Learning | Lex Fridman Podcast #36
Related Questions