16 September 1992 Shift-invariant neural network for image processing: learning and generalization
Author Affiliations +
We have applied a shift-invariant back propagation neural network to the cells' boundary detection of human corneal endothelium photomicrographs. The interconnection patterns of the neural network are constrained to be spatially invariant. Our experiments demonstrated that the generalizing ability of the neural network is dependent on its connectivity or complexity, i.e., the number of connections. To get a better generalization, we have proposed a modified back propagation learning rule, which reduces the complexity of the neural network during the learning procedure. The measure of the complexity of the neural network was defined as a formal entropy of the connectivity pattern. Simulations showed that the neural network trained by this learning rule has better generalizing ability but more computational complexity. In this paper a simplified function is investigated as the measure of the complexity of the neural network. This simplified measure is a first order approximation of the formal entropy measure. Simulations show that the simplified measure is effective to get better generalization and has less computational complexity than the original formal entropy measure.
© (1992) COPYRIGHT Society of Photo-Optical Instrumentation Engineers (SPIE). Downloading of the abstract is permitted for personal use only.
Wei Zhang, Wei Zhang, Akira Hasegawa, Akira Hasegawa, Osamu Matoba, Osamu Matoba, Kazuyoshi Itoh, Kazuyoshi Itoh, Yoshiki Ichioka, Yoshiki Ichioka, Kunio Doi, Kunio Doi, } "Shift-invariant neural network for image processing: learning and generalization", Proc. SPIE 1709, Applications of Artificial Neural Networks III, (16 September 1992); doi: 10.1117/12.140004; https://doi.org/10.1117/12.140004

Back to Top