The human brain is the most important organon our body. Moreover, We do not understand the mechanism of the brain due to the complexities. The brain is composed by various, really heavy neurons. Electroencephalogram (EEG) is spontaneous cortical electrical activity at the scalp. This signal is the electrophysiological response of cortical brain cells. It is now thought that the electrical potentials recorded as EEG are produced by electrical dipoles in the pyramidal cell layer. The important problem in the neural active study based on EEG measurement is the localization of these electrical dipoles. Given suitable models for source and head, the optimal solution by some well-known mathematical mathods can be obtained based on EEG potentials measured on the scalp. If we keep on listening to cyclic aural stimulation, may racall of it. During recall of it, we have the some signal source as it in brain. The purpose of this study is clarification of brain function from EEG. EEG recording system is based on the electrodes arrangement of a 10–20 system that include 2 reference electrodes. The aural stimulation is 1-cyclic sine wave that is 2 kHz. The experiment was conducted in radio anechoic chamber and when the eye was open to do alpha-suppession. Techniques for brain signal source localizationfrom EEG are artificial Neural-networks and Powell algorithm. In this case, in order to install a desired inverse function to the neural-networks, it should be trained by training data. Artificial Neural-networks learning algorithm is Back propagation.