Naslov
Discrete Time Neural Network Synthesis Using Input and Output Activation Functions

Autori
Novaković, Branko

Izvornik
IEEE Transactions on systems, man and cybernetics - part B : cybernetics (1083-4419) 26 (1996), 4; 533-541

Vrsta, podvrsta i kategorija rada
Radovi u časopisima, članak, znanstveni

Ključne riječi
Neural networks; one-step learning; input and output activation functions; discrete time

Sažetak
Abstract - A new very fast algorithm for synthesis of a new structure of discrete-time neural networks (NN) is proposed. For this purpose the following concepts are employed: (i) combination of input and output activation functions, (ii) input time-varying signal distribution, (iii) time-discrete domain synthesis and (iiii) one-step learning iteration approach. The problem of multiple input-output mappings of ( time-varying ) vectors is solved. Simulation results based on the synthesis of a new structure of feedforward NN of an universal logical unit are presented. The proposed NN synthesis procedure is useful for applications to identification and control of nonlinear, very fast, dynamical systems. In this sense a feedforward NN for an adaptive nonlinear robot control is designed. Finally, a new algorithm for the direct inverse modelling of input/output nonquadratic systems is discussed.

Izvorni jezik
Engleski

Znanstvena područja
Strojarstvo

POVEZANOST RADA