DL
Deep learning sample efficiency
Topic
What experts have said about Deep learning sample efficiency
1 statement · 1 negative
Poor sample efficiency forces deep-learning systems to use many parallel rollouts.
“the reason, by the way, you need to do so many parallel rollouts in order to learn a skill currently with deep learning is that we haven't solved sample efficiency.”
Open the episode · Grant Sanderson – AI and the future of mathListen at 54:51
Statements are attributed to the speaker as said on the episode and reflect their view at the time, not PodLume's. They are not advice.