A concept learning network based on correlation and backpropagation

A new concept learning neural network is presented. This network builds cor relation learning into a rule learning neural network where the certainty f actor model of traditional expert systems is taken as the network activatio n function. The main argument for this approach is that correlation learnin g can help when the neural network fails to converge to the target concept due to insufficient or noisy training data. Both theoretical analysis and e mpirical evaluation are provided to validate the system.