Kourosh Parand - Department of Computer Sciences, ShahidBeheshti University, G.C., Tehran, Iran.Department of Cognitive Modelling, Institute for Cognitive and Brain Sciences, ShahidBeheshti University, G.C., Tehran, Iran
Soleiman Hashemi - Department of Computer Sciences, ShahidBeheshti University, G.C., Tehran, Iran,
Amin Ghaderi - Department of Computer Sciences, ShahidBeheshti University, G.C., Tehran, Iran

In this examination, a new approach based on single layer Gegenbauer Artificial neural network to solve the MHD Falkner–Skan equation on the semi-infinite domain has been proposed. Here, the feed forward neural network model of the unsupervised type has been applied and also the error back propagation algorithm uses to train and update the network parameters. The hidden layer is omitted by applying a series expansion of Gegenbauer’s polynomials. To demonstrate reliability of the method, we compared the analytical outcomes

GegenbauerArtificial neural network,Feed forward Neural Network, Error back Propagation algorithm, Differential equations