Bossley, K.M., Mills, D.J., Brown, M. and Harris, C.J.
Construction and Design of Parsimonious Neurofuzzy Systems.
Neural Network Engineering in Control
Full text not available from this repository.
Static fuzzy systems have been extensively applied in the Far East to a wide range of consumer products whereas researchers in the west have mainly been concerned with developing adaptive neural network that can learn to perform ill-defined, difficult tasks. Neurofuzzy systems attempt to combine the best aspects of each of these techniques as the transparent representation of a fuzzy system is fused with the adaptive capabilities of a neural network, while minimising the undesirable features. As such, they are applicable to a wide range of static, design problems and on-line adaptive modelling and control applications. This chapter focuses on how an appropriate structure for the rule base may be determined directly from a set of training data. It provides the designer with valuable qualitative information about the physics of the underlying process as well as improving the network's generalisation abilities and the condition of the learning problem.
Actions (login required)