LOCAL CLUSTER NEURAL-NET - ARCHITECTURE, TRAINING AND APPLICATIONS

This paper describes the structure, training and computational abiliti es of the local cluster (LC) artificial neural net architecture. LC ne ts are a special class of multilayer perceptrons that use sigmoid func tions to generate localised functions. LC nets train as fast as radial basis functions nets and are more general. They are well suited for b oth, multi-dimensional function approximation and discrete classificat ion. The LC net is the result of our search for a widely applicable ne ural net architecture suitable for low-cost hardware realisation. The LC net seem particularly well suited for analog VLSI realisation of sm all-size, low-power, fully parallel neural net chip for real time cont rol applications. (C) 1998 Elsevier Science B.V. All rights reserved.