The Radial Basis Function (RBF) neural network has gained in popularity over recent years because of its rapid training and its desirable properties in classification and functional approximation applications. RBF network research has focused on enhanced training algorithms and variations on the basic architecture to improve the performance of the network. In addition, the RBF network is proving to be a valuable tool in a diverse range of application areas, for example, robotics, biomedical engineering, and the financial sector. The two volumes provide a comprehensive survey of the latest developments in this area. Volume 1 covers advances in training algorithms, variations on the architecture and function of the basis neurons, and hybrid paradigms, for example RBF learning using genetic algorithms. Both volumes will prove extremely useful to practitioners in the field, engineers, researchers and technically accomplished managers.

Contains a wide range of applications in the laboratory and case-studies describing current use Overall view of the methods used for the genetic optimisation of artificial neural networks and presentation of the inherent problems Includes supplementary material: sn.pub/extras

Inhalt
Dynamic RBF networks.- A hyperrectangle-based method that creates RBF networks.- Hierarchical radial basis function networks.- RBF neural networks with orthogonal basis functions.- On noise-immune RBF networks.- Robust RBF networks.- An introduction to kernel methods.- Unsupervised learning using radial kernels.- RBF learning in a non-stationary environment: the stability-plasticity dilemma.- A new learning theory and polynomial-time autonomous learning algorithms for generating RBF networks.- Evolutionary optimization of RBF networks.