Recurrent neural network synthesis using interaction activation functions
Branko M. Novakovic · 2002
A new very fast algorithm for synthesis of recurrent discrete-time neural networks (NN) is proposed. For this purpose the following concepts are employed: (i) introduction of interaction activation functions, (ii) time-varying NN weights distribution, (iii) time-discrete domain synthesis and (iv) one-step learning iteration approach. The proposed NN synthesis procedure is useful for applications to identification and control of nonlinear, very fast, dynamical systems. In this sense a recurrent NN for a nonlinear robot control is designed.