Re:Applications of Deep Neural Networks v2 [pdf]
by notretarded on Monday January 25, 2021 @04:04AM
(#25901061)
It's not penalty or step size. It's loss as in amount of information lossd (not encoded in your network) compared to one perfectly encoding ground truth.
Learning rate, as in what is the maximum amount of delta you are allowed to change your inputs to minimise your information loss analogous to how quickly you can possibly learn in one experiment.
[ Parent
| on HN ]
Re:Applications of Deep Neural Networks v2 [pdf]
by sillysaurusx on Monday January 25, 2021 @04:14AM
(#25901132)
Fair. I’ll keep that in mind. On the other hand, it went way over my head, and I’m not afraid to admit it.
One of the nice things about ML (and math, for that matter) is that there are multiple mathematically equivalent ways of looking at a thing.