It's great works. Awesome.

[ccckmit]

I really love adnn. It's beautiful and powerful. Thank you.

I am trying to work out some example for adnn.

An simple nnXor.js example run successfully as following.

https://github.com/ccckmit/ai6/tree/master/book/nn/adnn

But for the nnMlp.js example, the network output fail to approximate the training data.

https://github.com/ccckmit/ai6/blob/master/book/nn/adnn/nnMlp.js

Do I use the wrong optimization method ?

I don't know why ?