International Journal of Artificial Intelligence and Neural Networks
Author(s) : PRAVEEN KUMAR, V.S.S KUMAR
Many problems of the real world vary with number of parameters affecting the system and their computations become a difficult task. Artificial neural networks (ANN) can learn and be trained on a set of input and output data belonging to a particular problem. The field applications of Artificial Intelligence have increased dramatically in the past few years. ANN is built from a large number of processing elements that individually deal with pieces of a big problem. If new data of the problem are presented to the system, the ANN can use the learned data to predict outcomes without any specific programming relating to the category of events involved. A large variety of possible ANN applications now exist for non computer specialists. Therefore, with a very modest knowledge of the theory behind ANN, it is possible to tackle complicated problems in a researcher's own area of specialty with the ANN techniques. ANN learning occurs through training to a set of input and output data, where the training algorithm iteratively adjusts the connection weights. In the present paper an overview of ANN has been discussed for cognitive decision making.