Title :
Local minima and back propagation
Author :
Poston, Timothy ; Lee, Chung-Nim ; Choie, YoungJu ; Kwon, YongHoon
Author_Institution :
Dept. of Math., Pohang Inst. of Sci. & Technol., South Korea
Abstract :
It is shown that, in a feedforward net of logistic units, if there are as many hidden nodes as patterns to learn then almost certainly a solution exists, and the error function has no local minima. A large enough feedforward net can reproduce almost any finite set of targets for almost any set of input patterns, and will almost certainly not be trapped in a local minimum while learning to do so
Keywords :
learning systems; neural nets; back-propagation; error function; feedforward net; local minima; Equations; Feedforward neural networks; Logistics; Mathematics; Neural networks; Nonhomogeneous media; Testing;
Conference_Titel :
Neural Networks, 1991., IJCNN-91-Seattle International Joint Conference on
Conference_Location :
Seattle, WA
Print_ISBN :
0-7803-0164-1
DOI :
10.1109/IJCNN.1991.155333
