|
S.A. Gladilin, D.P. Nikolaev, D.V. Polevoi, N.A. Sokolova Study of Multilayer Perceptron Accuracy Improvement under Fixed Number of Neuron |
|
Abstract.In this article multilayer perceptron accuracy improvement of real time recognition system under time limitations was explored. To solve this task two level tree of classifiers was used. The top level of the tree is a fast selector gotten without supervised training, and the bottom level is a set of neural net classifiers trained on the corresponding training sets. These scheme allows to increase the number of neurons used in recognition under the same processing time, that helps to increase generalisation power of the classifier. Recognition of embossed symbols on plastic cards was used as model task. Keywords: machine learning, OCR, multilayer perceptron, feature spaces, real time recognition systems. PP. 96-105. REFERENCES 1. Masoudnia, S., Ebrahimpour, R., “Mixture of experts: a literature survey”, Artificial Intelligence Review, (2012). 2. Wozniak, M., Grana, M., & Corchado, E. “A survey of multiple classifier systems as hybrid systems”, Information Fusion, 16(13), 3–17 (2014). 3. Dietterich, T. G., “Ensemble Methods in Machine Learning”, Multiple Classifier Systems SE - 1 (Vol. 1857, pp. 1–15), (2000). 4. Giacinto, G., & Roli, F., “Dynamic Classifier Selection”, Proceedings of the First International Workshop on Multiple Classifier Systems (pp. 177–189). London, UK, UK: Springer-Verlag, (2000). 5. Ko, A. H. R., Sabourin, R., & Britto, Jr., A. S., “From dynamic classifier selection to dynamic ensemble selection”, Pattern Recognition, 41(5), 1718–1731, (2008). 6. Steinhaus H. “Sur la division des corps materiels en parties”, Bull. Acad. Polon. Sci., C1. III vol. IV: 801—804, (1956). 7. Jain, A. K., & Lansing, E., “Data Clustering”, 50 Years Beyond K-Means Michigan State University, (2009).
|