Title :
A local minimum for the 2-3-1 XOR network
Author :
Sprinkhuizen-Kuyper, Ida G. ; Boers, Egbert J W
Author_Institution :
Dept. of Comput. Sci., Leiden Univ., Netherlands
fDate :
7/1/1999 12:00:00 AM
Abstract :
It was assumed proven that two-layer feedforward neural networks with t-1 hidden nodes, when presented with t input patterns, can not have any suboptimal local minima on the error surface. In this paper, however, we shall give a counterexample to this assumption. This counterexample consists of a region of local minima with nonzero error on the error surface of a neural network with three hidden nodes when presented with four patterns (the XOR problem). We will also show that the original proof is valid only when an unusual definition of local minimum is used
Keywords :
feedforward neural nets; minimisation; multilayer perceptrons; 2-3-1 XOR network; EXOR network; nonzero error; suboptimal local minima; two-layer feedforward neural networks; Computer errors; Computer science; Feedforward neural networks; Neural networks; Transfer functions;
Journal_Title :
Neural Networks, IEEE Transactions on
