Neural Network Reasoning
Petar discusses the importance of neural networks in reasoning and extrapolation, highlighting the challenges faced in closed versus open environments. He emphasizes the need for models to extrapolate knowledge for future scenarios, especially in the realm of artificial general intelligence.In this clip
From this podcast
Machine Learning Street Talk (MLST)
#60 Geometric Deep Learning Blueprint (Special Edition)
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?