[8note]

http://imgur.com/ypBQEWx

Add some noise, and use all the inputs, and one 8 wide hidden layer

edit: works better with a sigmoid activation curve, but it converges more slowly

[andrewtbham]

Yeh you're on the right track. Nice pattern emerges on this after 160 iterations.

http://playground.tensorflow.org/#activation=tanh&batchSize=...

[rmellow]

Using syn, cos, x1, x2 with 1 six-neuron hidden layer does the trick quickly: http://imgur.com/UMv5gsH

No need to mess with noise or regularization :)

[makeset]

> Add some noise

This actually makes the dataset harder to fit to. It is not the same thing here as the "training with noise" method where random noise would be added to each batch, as an alternative means of Tikhonov regularization.

[8note]

wih that particular data set, it looks like it really just adds more data, and more importantly, fills in the gaps along the spirals which is where my setup was having troubles.

The noise doesn't go far enough to start confusing points between different clusters, but it adds more points.

That said, my knowledge of neural nets is fairly limited.

[cglace]

Using all inputs and 6 layers of varying sizes. After about 500 iterations. http://i.imgur.com/x1MOpvl.jpg

[visarga]

Just 100 iterations, learning rate 0.03, activation tanh, regularization L2, rate 0.01. The network is 8,8,8 neurons per layer.