caa a22 4500 475801180 CHVBK 20180406123737.0 cr unu---uuuuu 170329e20000401xx s 000 0 eng 10.1023/A:1009640416018 doi (NATIONALLICENCE)springer-10.1023/A:1009640416018 An Incremental Algorithm for Parallel Training of the Size and the Weights in a Feedforward Neural Network [Elektronische Daten] [Kateřina Hlaváčková-Schindler, Kateřina Hlaváčková-Schindler, Manfred Fischer] An algorithm of incremental approximation of functions in a normed linearspace by feedforward neural networks is presented. The concept of variationof a function with respect to a set is used to estimate the approximationerror together with the weight decay method, for optimizing the size andweights of a network in each iteration step of the algorithm. Two alternatives, recursively incremental and generally incremental, are proposed. In the generally incremental case, the algorithm optimizes parameters of all units in the hidden layer at each step. In the recursively incremental case, the algorithm optimizes the parameterscorresponding to only one unit in the hidden layer at each step. In thiscase, an optimization problem with a smaller number of parameters is beingsolved at each step. Kluwer Academic Publishers, 2000 approximation of a function nationallicence feedforward network nationallicence incremental algorithm nationallicence variation of a function with respect to a set nationallicence weight decay nationallicence Hlaváčková-Schindler Kateřina Institute for Urban and Regional Research, Austrian Academy of Sciences, Postgasse 7/4/2, A-1010, Vienna, Austria aut Hlaváčková-Schindler Kateřina Institute of Computer Science, Academy of Sciences of the Czech Republic, Pod Vadárenskou věží 2, 18207 Praha 8, Czech Republic aut Fischer Manfred Department of Economic and Social Geography, Wirtschaftsuniversität Wien, Augasse 2-6, A-1090, Vienna, Austria aut Neural Processing Letters Kluwer Academic Publishers 11/2(2000-04-01), 131-138 1370-4621 11:2<131 2000 11 11063 https://doi.org/10.1023/A:1009640416018 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1023/A:1009640416018 text/html Onlinezugriff via DOI NATIONALLICENCE 700 1- Hlaváčková-Schindler Kateřina Institute for Urban and Regional Research, Austrian Academy of Sciences, Postgasse 7/4/2, A-1010, Vienna, Austria aut NATIONALLICENCE 700 1- Hlaváčková-Schindler Kateřina Institute of Computer Science, Academy of Sciences of the Czech Republic, Pod Vadárenskou věží 2, 18207 Praha 8, Czech Republic aut NATIONALLICENCE 700 1- Fischer Manfred Department of Economic and Social Geography, Wirtschaftsuniversität Wien, Augasse 2-6, A-1090, Vienna, Austria aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers 11/2(2000-04-01), 131-138 1370-4621 11:2<131 2000 11 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer