
MIT’s Jonathan Frankle on “The Lottery Hypothesis” - Ep. 115
NVIDIA AI Podcast
00:00
The Importance of Capacity in Learning
When you create a neural network, it's not just about how all the connections are configured. It's also about how you initialize them. The going thinking was that during the learning process, it takes a lot of capacity. And so let me finally answer your original question about, what is this lottery ticket hypothesis idea? Yeah. To do that, I need to tell you one more thing about neural networks.
Play episode from 05:06
Transcript


