Hacker News Reader

20,000 rounds for the NN to learn XOR?

Is this typical for this level of task?

By tweaking the learning rate I managed to lower the iterations/rounds to 750.

For my own test project I only did 10k iterations/.3 learning rate on a 16 input, 32 hidden, and 1 output neuron network and my early tests on my "non-math" problem seemed good.

How about creating a fork and explaining what you did to get the iterations down to 750? :)

Interesting, thanks. That's a pretty good decrease in rounds.

Reply on news.ycombinator.com