Twitter | Pretraživanje | |
KordingLab 👨‍💻🧠∇🔬📈,🏋️‍♂️⛷️🏂🛹🕺⛰️☕🦖 1. pro
I think that the brain almost certainly approximates gradient descent. And here is why: Any learning episode only appears to change the brain a tiny bit. 1/5
Reply Retweet Označi sa "sviđa mi se"
Barak A. Pearlmutter 9. pro
Odgovor korisniku/ci @KordingLab
I thought "Intrinsic Gradient Networks", Jason Tyler Rolfe's PhD Thesis (2012, doi:10.7907/YCB7-7X24. ) was an underappreciated approach to the problem of 𝛁∈🧠
Reply Retweet Označi sa "sviđa mi se"
KordingLab 👨‍💻🧠∇🔬📈,🏋️‍♂️⛷️🏂🛹🕺⛰️☕🦖 9. pro
Odgovor korisniku/ci @BAPearlmutter
Omg. Why didn't I know of it!
Reply Retweet Označi sa "sviđa mi se"
Blake Richards 9. pro
Odgovor korisniku/ci @KordingLab @BAPearlmutter
Ditto!
Reply Retweet Označi sa "sviđa mi se"
Adam Marblestone 10. pro
Odgovor korisniku/ci @tyrell_turing @KordingLab i 2 ostali
Fascinating that one of the intrinsic gradient networks is... belief propagation. Rolfe’s earlier MS thesis has a dendritic + columnar model for sum-product BP. Once can do BP itself, gradient of BP is easy. Comes full circle with ’s comments on the brain GD issue?
Reply Retweet Označi sa "sviđa mi se"
Dileep George 10. pro
Adam, do you have a link to his MS thesis?
Reply Retweet Označi sa "sviđa mi se"
Adam Marblestone 10. pro
Reply Retweet Označi sa "sviđa mi se"
Adam Marblestone
(With these bits he basically sets the stage for 6 years later saying BP is an “intrinsic gradient“ system and then generalized that concept to other dynamics like specific kinds of RNNs...)
Reply Retweet Označi sa "sviđa mi se" More