Yoshua Bengio: Deep Learning
Lex Fridman Podcast
00:00
Is It an Architecture Challenge or a Data Set Challenge?
Data sets on architecturesr something you want to always play with. But i think the crucial thing is more the training objective, the training frameworks. The relationships between causes and effects. Are the sort of objective functions which could be important to allow the highest level a explanations to to rise from from the learning? I'm tempted to send it there nose your library. Us.
Transcript
Play full episode
