Episode 26: Sugandha Sharma, MIT, on biologically inspired neural architectures, how memories can be implemented, and control theory
Generally Intelligent
00:00
Learning Weights for Decoders
In Chris' lab, they were just using a simple optimization procedure. So, it was just minimizing the least squares error between what the original, the target output and the output that you're getting. How are the weights for the decoders? It's not backdrop, right? Or is there just done randomly? Or like how do people do this in the neuroscience side of things?
Transcript
Play full episode
