How to teach a Bayesian spam filter to play chess

Re:How to teach a Bayesian spam filter to play chess by zyroth on Friday November 02, 2007 @07:49PM (#75647)

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.

[ Parent | on HN ]

Re:How to teach a Bayesian spam filter to play chess by pixcavator on Friday November 02, 2007 @08:07PM (#75657)

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?

[ Parent | on HN ]

Re:How to teach a Bayesian spam filter to play chess by zyroth on Saturday November 03, 2007 @05:47AM (#75746)

Training examples.

[ Parent | on HN ]

Re:How to teach a Bayesian spam filter to play chess by pixcavator on Saturday November 03, 2007 @07:26AM (#75751)

Computers can form concepts, really?

[ Parent | on HN ]

Re:How to teach a Bayesian spam filter to play chess by zyroth on Saturday November 03, 2007 @10:04AM (#75777)

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

[ Parent | on HN ]