engleski

A New Structure of Discrete Time Neural Networks

A new structure of discrete-time neural networks (NN) with a new very fast learning algorithm 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. A new algorithm for the direct inverse modelling of input/output nonquadratic systems is discussed. 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.

Discrete time neural networks; new structure; very fast learning

nije evidentirano