Title :
Inversion of multilayer nets
Author :
Linden, A. ; Kindermann
Author_Institution :
Ges. Fuer Math. & Datenverarbeitung GmbH, Sankt Augustin, West Germany
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;
Conference_Titel :
Neural Networks, 1989. IJCNN., International Joint Conference on
Conference_Location :
Washington, DC, USA
DOI :
10.1109/IJCNN.1989.118277
