On: How to teach a Bayesian spam filter to play chess

[zyroth]

No, I'm saying that a neural network can learn addition.

See, a bayesian cannot really understand that there are relations between two numbers (like "is bigger than" or "is the following number of"), but a neural network can, since addition is part of a NN.

My personal recommendation on machine learning is 'Pattern Recognition and Machine Learning' by Chris Bishop. But you definately do need a solid mathematical background for that.

[pixcavator → zyroth]

Where would the idea of "is bigger than" or "is the following number of" come from if not from the person who creates the network?

[zyroth → pixcavator]

Training examples.

[pixcavator → zyroth]

Computers can form concepts, really?

[zyroth → pixcavator]

If you want them to learn a specific concept that we know, they can learn it, yes.