DocumentCode :
3229555
Title :
Inversion of multilayer nets
Author :
Linden, A. ; Kindermann
Author_Institution :
Ges. Fuer Math. & Datenverarbeitung GmbH, Sankt Augustin, West Germany
fYear :
1989
fDate :
0-0 1989
Firstpage :
425
Abstract :
The method of inversion for arbitrary continuous multilayer nets is developed. The inversion is done by computing iteratively an input vector which minimizes the least-mean-square errors to approximate a given output target. This inversion is not unique for given targets and depends on the starting point in input space. The inversion method turns out to be a valuable tool for the examination of multilayer nets (MLNs). Applications of the inversion method to constraint satisfaction, feature detection, and the testing of reliability and performance of MLNs are outlined. It is concluded that recurrent nets and even time-delay nets might be invertible.<>
Keywords :
least squares approximations; neural nets; constraint satisfaction; even time-delay nets; feature detection; input vector; inversion; least-mean-square errors; multilayer nets; output target; recurrent nets; reliability; Least squares methods; Neural networks;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
Type :
conf
DOI :
10.1109/IJCNN.1989.118277
Filename :
118277
Link To Document :
بازگشت