
Episode 26: Sugandha Sharma, MIT, on biologically inspired neural architectures, how memories can be implemented, and control theory
Generally Intelligent
00:00
Deep Learning
When we think about deep learning or even back-proper training weights through back-pro, sometimes what you're learning becomes very restrictive. And also, the other thing is that it takes a long time for you to train. You want your capacity to be higher, given that even humans are remembering loads and loads of information through our lifetimes. That's what I think. Did you have any other questions about this? No, I mean, I think one sort of, this is a little bit of a tent and we'll come back to the overall journey. But I guess, since you have worked on, or I guess, have you done any work when deep learning and other ways
Transcript
Play full episode