2 November 2000 Analyzing decision boundaries of neural networks
Author Affiliations +
Abstract
In this paper, we analyze decision boundaries of 3 layer feedforward neural networks that use the sigmoid function as an activation function. By analyzing the decision boundaries in the space defined by the outputs of the hidden neurons, we found that the decision boundaries are always linear boundaries and that the decision boundaries are not completely independent. We found that for a 3-pattern class problem, the decision boundaries in the space defined by the outputs of the hidden neurons should meet at the same intersection. And this dependency of decision boundaries is extended to multiclass problems, providing valuable insight into decision boundaries. In particular, for a K-pattern classes problems, we found that there are only K-1 degree of freedoms in drawing decision boundaries in the space defined by the outputs of the hidden neurons, though there are KC2 decision boundaries. Finally, we present some interesting examples of decision boundaries of neural networks.
© (2000) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Chulhee Lee, Eunsuk Jung, "Analyzing decision boundaries of neural networks", Proc. SPIE 4113, Algorithms and Systems for Optical Information Processing IV, (2 November 2000); doi: 10.1117/12.405857; https://doi.org/10.1117/12.405857
PROCEEDINGS
10 PAGES


SHARE
Back to Top