Episode 26: Sugandha Sharma, MIT, on biologically inspired neural architectures, how memories can be implemented, and control theory
Generally Intelligent
00:00
Is There a Need to Sync Theory and Experiment in Neuroscience?
I think neuroscience is such an open field, that there's so many important questions. My perspective is that we really need to sync theory and experiment. We can test the predictions made by our models, and then come back and correct our models based on the experiments and experimental findings. And one kind of an idea that I have in this direction is, in the map induction work, we kind of build in some metric priors,. But then, thinking more in a more abstract domain, you can think of this as graph induction.
Transcript
Play full episode
