swarm optimized functional link artificial neural network

Multilayer perceptron (MLP) (trained with back propagation learning algorithm) takes large computational time. The complexity of the network increases as the number of layers and number of nodes in layers increases. Further, it is also very dif?cult to decide the number of nodes in a layer and the number of layers in the network required for solving a problem a priori. In this paper an improved particle swarm optimization (IPSO) is used to train the functional link arti?cial neural network (FLANN) for classi?cation and we name it ISO-FLANN. In contrast to MLP, FLANN has less architectural complexity, easier to train, and more insight may be gained in the classi?cation problem. Further, we rely on global classi?cation capabilities of IPSO to explore the entire weight space, which is plagued by a host of local optima. Using the functionally expanded features; FLANN overcomes the non-linear nature of [login to view URL] believe that the combined efforts of FLANN and IPSO (IPSO + FLANN = ISO − FLANN) by harnessing their best attributes can give rise to a robust classi?er. An extensive simulation study is presented to show the effectiveness of proposed classi?er. Results are compared with MLP, support vector machine(SVM) with radial basis function (RBF) kernel, FLANN with gradiend descent learning and fuzzy swarm net (FSN).