caa a22 4500 477034411 CHVBK 20180405111301.0 cr unu---uuuuu 170330e19960401xx s 000 0 eng 10.1007/BF00417785 doi (NATIONALLICENCE)springer-10.1007/BF00417785 Ciocoiu Iulian Faculty of Electronics and Telecommunications, Technical University Iasi, P.O. Box 877, 6600, Iasi, Romania aut Radial basis function networks with FIR/IIR synapses [Elektronische Daten] [Iulian Ciocoiu] A learning algorithm for a special class of Radial Basis Functions (RBF) networks is proposed. The novelty aspect of the architecture consists in replacing the usual scalar values of the output weights with linear FIR or IIR filters transfer functions. Simulation results for approximating a lowpass Butterworth filter are presented and other potential temporal processing applications are outlined. Kluwer Academic Publishers, 1996 local recurrent architectures nationallicence RBF networks nationallicence Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 3/1(1996-04-01), 17-22 1370-4621 3:1<17 1996 3 11063 https://doi.org/10.1007/BF00417785 text/html Onlinezugriff via DOI 1 research-article jats NATIONALLICENCE 856 40 https://doi.org/10.1007/BF00417785 text/html Onlinezugriff via DOI NATIONALLICENCE 100 1- Ciocoiu Iulian Faculty of Electronics and Telecommunications, Technical University Iasi, P.O. Box 877, 6600, Iasi, Romania aut NATIONALLICENCE 773 0- Neural Processing Letters Kluwer Academic Publishers; http://www.wkap.nl 3/1(1996-04-01), 17-22 1370-4621 3:1<17 1996 3 11063 Metadata rights reserved Springer special CC-BY-NC licence nationallicence BK010053 XK010053 XK010000 NATIONALLICENCE NATIONALLICENCE NL-springer