
A Conversation Between Terry Sejnowski & Stephen Wolfram (February 14, 2023) [Part 2]
The Stephen Wolfram Podcast
00:00
Is It Possible to Reduce a Loss in a Neural Network?
The whole thing has to come to equilibrium, all the parts and they have to trade information. This is specifically for a neural net because it's just the panel case. If you're training it to do some kind of categorization or just any function, any, you're going from input to output function. You could minimize that over time. And again, if there's a network that is able to do that transformation or categorization, then both of the machine could find it.
Transcript
Play full episode