061: Interpolation, Extrapolation and Linearisation (Prof. Yann LeCun, Dr. Randall Balestriero)
Machine Learning Street Talk (MLST)
Do We Really Want Distinctive Reasoning?
The speaker discusses the concept of discreet reasoning with a neural network. They question whether it's a good thing to have and whether it should be a part of the main model. They explore the idea of learning and differential intelligence. They also discuss energy minimization and the use of a minimization algorithm at test time. Overall, they ponder the importance of discreet reasoning in models and its implications.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.
