News for hackers. Stuff that matters.

A comment on What's Wrong with Deep Learning?. Parent comment

Re:What's Wrong with Deep Learning? by ma2rten on Sunday June 14, 2015 @04:46PM (#9716278)
Lack of theory is actually mentioned as one of the issues in the presentations.

I don't think your examples are good though, Max polling reduces noise. RuLU learn faster than Sigmoid or tanh.

[ Parent | on HN ]
Re:What's Wrong with Deep Learning? by kmicklas on Sunday June 14, 2015 @06:26PM (#9716548)
> I don't think your examples are good though, Max polling reduces noise. RuLU learn faster than Sigmoid or tanh.

That's not theory, that's just observation of the results. Why should we expect it to work that way?

[ Parent | on HN ]