DocumentCode :
3323583
Title :
Characteristics of the functional link net: a higher order delta rule net
Author :
Klassen, Myungsook ; Pao, Yoh Han ; Chen, Victor
Author_Institution :
Center for Autom. & Intelligent Syst. Res., Case Western Reserve Univ., Cleveland, OH, USA
fYear :
1988
fDate :
24-27 July 1988
Firstpage :
507
Abstract :
Reports on the characteristics of a net which incorporates higher-order effects in supervised learning in ways different from those previously proposed. These higher-order effects are introduced through nonlinear functional transforms via links rather than at nodes. Specific instances include transforming the input vector into higher-order tensors. Learning-rate increases, for several examples, are described. Network architecture simplifications are also described.<>
Keywords :
artificial intelligence; neural nets; transforms; artificial intelligence; delta rule net; functional link net; input vector; learning rate; neural nets; tensors; Artificial intelligence; Neural networks; Transforms;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1988., IEEE International Conference on
Conference_Location :
San Diego, CA, USA
Type :
conf
DOI :
10.1109/ICNN.1988.23885
Filename :
23885
Link To Document :
بازگشت