Maxout Networks — mentioned by eru

Tue, 03 Oct 2017 12:09:39 GMT

Current AI approaches don't have that much to do with the biological brain. Despite the name 'neuronal networks' that we have history to thank for, it's better think of them as just long compositions of functions with a lot of parameters one can tweak. Historically researchers looked at activation functions that are at least somewhat justified by nature, like the sigmoid. More recently people have focused on the mathematical aspects and figured out that the rectified liner unit `ReLU(x) = max(x, 0)` works just as well if not better for most applications. Maxout networks…

Paper and discussion history. A mention is not an endorsement.

Maxout Networks · HackerPapers discussions

Maxout Networks — mentioned by eru