Browse > Article
http://dx.doi.org/10.5762/KAIS.2014.15.3.1724

Pattern Recognition Analysis of Two Spirals and Optimization of Cascade Correlation Algorithm using CosExp and Sigmoid Activation Functions  

Lee, Sang-Wha (Department of Information & Communication Engineering, Seowon University)
Publication Information
Journal of the Korea Academia-Industrial cooperation Society / v.15, no.3, 2014 , pp. 1724-1733 More about this Journal
Abstract
This paper presents a pattern recognition analysis of two spirals problem and optimization of Cascade Correlation learning algorithm using in combination with a non-monotone function as CosExp(cosine-modulated symmetric exponential function) and a monotone function as sigmoid function. In addition, the algorithm's optimization is attempted. By using genetic algorithms the optimization of the algorithm will attempt. In the first experiment, by using CosExp activation function for candidate neurons of the learning algorithm is analyzed the recognized pattern in input space of the two spirals problem. In the second experiment, CosExp function for output neurons is used. In the third experiment, the sigmoid activation functions with various parameters for candidate neurons in 8 pools and CosExp function for output neurons are used. In the fourth experiment, the parameters are composed of 8 pools and displacement of the sigmoid function to determine the value of the three parameters is obtained using genetic algorithms. The parameter values applied to the sigmoid activation functions for candidate neurons are used. To evaluate the performance of these algorithms, each step of the training input pattern classification shows the shape of the two spirals. In the optimizing process, the number of hidden neurons was reduced from 28 to15, and finally the learning algorithm with 12 hidden neurons was optimized.
Keywords
Activation function; Cascade correlation algorithm; Cosine-modulated symmetric exponential function; Sigmoid function;
Citations & Related Records
Times Cited By KSCI : 1  (Citation Analysis)
연도 인용수 순위
1 Fahlman, S. E. and Lebiere, C., "he Cascade-Correlation Learning Architecture", Advances in Neural Information Processing Systems 2, D. S. Touretzky (ed.), Morgan-Kaufmann, Los Altos CA., 1990.
2 Prechelt, L., "PROBEN1-A Set of Neural Network Benchmark Problems and Benchmarking Rules", Technical Report 21/94, Department of Computer Science, University of Karlsruhe, September 30, 1999.
3 Thomas R. Shultz, Scott E. Fahlman, "Cascade-Correlation", Encyclopedia of Machine Learning, pp.139-147, 2010
4 Ikuta. C, Uwate Y. and Nishio Y., "Chaos Glial Network connected to Multi-Layer Perceptron for Solving Two-Spiral Problem", Proc. ISCAS'10, May, 2010.
5 Sang-Wha Lee, "Optimization of sigmoid activation Function parameters using genetic algorithms and pattern recognition analysis in input space of two spirals problem", The korea contents association, v.10, No.4, pp.10-18, 4. 2010. DOI: http://dx.doi.org/10.5392/JKCA.2010.10.4.010   과학기술학회마을   DOI   ScienceOn