Zhou, Yongquan; Zhao, Bin; Jiao, Licheng A recurrent function networks model and a learning algorithm. (Chinese. English summary) Zbl 1174.68535 Syst. Eng. Electron. 29, No. 10, 1727-1731 (2007). Summary: A new kind of recurrent functional network model is proposed, a general criterion on the stability of recurrent functional networks is given, and the stable points of the functional network are converted as the function fixed points. A learning algorithm of recurrent functional network is proposed, which adopted Lagrange multipliers as an auxiliary function and sums up the learning process of function parameters as solving a series of linear equations. Finally, the simulation results demonstrate that the learning algorithm presented in the paper has rapid convergence speed and powerful performance. MSC: 68T05 Learning and adaptive systems in artificial intelligence Keywords:recurrent functional networks; Lagrange multipliers; linear equations PDFBibTeX XMLCite \textit{Y. Zhou} et al., Syst. Eng. Electron. 29, No. 10, 1727--1731 (2007; Zbl 1174.68535)