caa a22 4500 465797709 CHVBK 20180323112043.0 cr unu---uuuuu 170327e19901201xx s 000 0 eng 10.1007/BF00439421 doi (NATIONALLICENCE)springer-10.1007/BF00439421 Learning algorithms for neural networks with the Kalman filters [Elektronische Daten] [Keigo Watanabe, Spyros Tzafestas] Based on various approaches, several different learing algorithms have been given in the literature for neural networks. Almost all algorithms have constant learning rates or constant accelerative parameters, though they have been shown to be effective for some practical applications. The learning procedure of neural networks can be regarded as a problem of estimating (or identifying) constant parameters (i.e. connection weights of network) with a nonlinear or linear observation equation. Making use of the Kalman filtering, we derive a new back-propagation algorithm whose learning rate is computed by a time-varying Riccati difference equation. Perceptron-like and correlational learning algorithms are also obtained as special cases. Furthermore, a self-organising algorithm of feature maps is constructed within a similar framework. Kluwer Academic Publishers, 1990 Neural nets nationallicence nonlinear filtering nationallicence Kalman filters nationallicence parameter estimation nationallicence learning systems nationallicence pattern recognition nationallicence Watanabe Keigo College of Engineering, Shizuoka University, Johoku 3-5-1, 432, Hamamatsu, Japan aut Tzafestas Spyros Division of Computer Science, Department of Electrical Engineering, National Technical University of Athens, Zografou, 15773, Athens, Greece aut Journal of Intelligent and Robotic Systems Kluwer Academic Publishers 3/4(1990-12-01), 305-319 0921-0296 3:4<305 1990 3 10846 https://doi.org/10.1007/BF00439421 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00439421 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Watanabe Keigo College of Engineering, Shizuoka University, Johoku 3-5-1, 432, Hamamatsu, Japan aut NATIONALLICENCE 700 1- Tzafestas Spyros Division of Computer Science, Department of Electrical Engineering, National Technical University of Athens, Zografou, 15773, Athens, Greece aut NATIONALLICENCE 773 0- Journal of Intelligent and Robotic Systems Kluwer Academic Publishers 3/4(1990-12-01), 305-319 0921-0296 3:4<305 1990 3 10846 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer