Re:Differentiable Plasticity: A New Method Learning to Learn
by dchichkov on Tuesday April 10, 2018 @07:14PM
(#16806515)
Itβd be interesting to compare this approach against a simpler baseline: setting a different (10 β 100 times higher?) learning rate for a fraction (10% ?) of neurons in an LSTM.
[ Parent
| on HN ]
Re:Differentiable Plasticity: A New Method Learning to Learn
by fizx on Tuesday April 10, 2018 @10:34PM
(#16807596)
Interesting... I mean knockout already does this (sort of), by setting the learning rate of 10% artificially low. I'm not sure if inverting the common thing is useful, but it might be fun to try.