An effective approach for medical diagnosis preceded by artificial neural network ensemble

This research is to search for alternatives to the resolution of complex medical diagnosis where human knowledge should be apprehended in a general fashion. Successful application examples show that human diagnostic capabilities are significantly worse than the neural diagnostic system. Then, paradigm of artificial neural networks is shortly introduced and the main problems of medical data base and the basic approaches for training and testing a network by medical data are described. A lot of Applications tried to help human experts, offering a solution. This paper describes a optimal feed forward Back propagation algorithm. However, Traditional Back propagation algorithm has many shortcomings. Learning often takes long time to converge, and it may fall into local minima. One of the possible remedies to escape from local minima is by using a very small learning rate, which slows down the learning process. The proposed algorithm presented in this study used for training depends on a multilayer neural network with a very small learning rate, especially when using a large training set size. It can be applied in a generic manner for any network size that uses a back propagation algorithm through an optimal time (seen time).