Abstract :
Comparison of various methods of computational intelligence are presented and illustrated with examples. These methods include neural networks, fuzzy systems, and evolutionary computation. The presentation is focused on neural networks, their learning algorithms and special architectures. General learning rule as a function of the incoming signals is discussed. Other learning rules such as Hebbian learning, perceptron learning, LMS (least mean square) learning, delta learning, WTA (winner take all) learning, and PCA (principal component analysis) are presented as a derivation of the general learning rule. Architecture specific learning algorithms for cascade correlation networks, Sarajedini and Hecht-Nielsen networks, functional link networks, polynomial networks, counterpropagation networks, RBF (radial basis function) networks are described.
Keywords :
Hebbian learning; cascade systems; evolutionary computation; fuzzy systems; least mean squares methods; perceptrons; principal component analysis; radial basis function networks; Hebbian learning; cascade correlation network; computational intelligence; counterpropagation network; delta learning; evolutionary computation; functional link network; fuzzy system; learning algorithm; least mean square learning; neural network; perceptron learning; polynomial network; principal component analysis; radial basis function network; winner take all learning; Computational intelligence; Computer architecture; Concurrent computing; Evolutionary computation; Feedforward neural networks; Fuzzy systems; Neural networks; Neurons; Parallel processing; Signal processing algorithms;