Browse > Article

Approximation of Polynomials and Step function for cosine modulated Gaussian Function in Neural Network Architecture  

Lee, Sang-Wha (Department of Information and Communication, Seowon University)
Publication Information
Journal of the Institute of Electronics Engineers of Korea CI / v.49, no.2, 2012 , pp. 115-122 More about this Journal
Abstract
We present here a new class of activation functions for neural networks, which herein will be called CosGauss function. This function is a cosine-modulated gaussian function. In contrast to the sigmoidal-, hyperbolic tangent- and gaussian activation functions, more ridges can be obtained by the CosGauss function. It will be proven that this function can be used to aproximate polynomials and step functions. The CosGauss function was tested with a Cascade-Correlation-Network of the multilayer structure on the Tic-Tac-Toe game and iris plants problems, and results are compared with those obtained with other activation functions.
Keywords
cosine-modulated gaussian function; Tic-Tac-Toe game problem; iris plants problem;
Citations & Related Records
연도 인용수 순위
  • Reference
1 B. DasGupta und G. Schnitger, "The Power of Approximating: a Comparison of Activation Functions", Advances in Neural Information Processing Systems5, Edited by R. P. Lippmann, J. E. Moody and D. S. Touretzky, Morgan Kaufmann, pp. 615-622, 1993.
2 B. DasGupta und G. Schnitger, "Efficient approximation with neural networks: A comparison of gate functions", Pennsylvania State University, 1993.
3 S. E. Fahlman and C. Lebiere, "The cascadecorrelation learning architecture," Advances in Neural Information Processing Systems 2, Morgan Kaufmann, 1990.
4 G. W. Flake, "Nonmonotonic activation functions in multilayer perceptrons", Dissertation, Institute for Advance Computer Studies department of Computer Science University of Maryland, 1993.
5 B. Hammer, A. Micheli and A. Sperduti, "Universal approximation capability of cascade correlation for structures," Neural Computation, Vol.17, No.5, pp.1109-1159, 2005.   DOI   ScienceOn
6 L. Prechelt, "PROBEN1-A Set of Neural Network Benchmark Problems and Benchmarking Rules," Technical Report 21/94, Department of Computer Science, University of Karlsruhe, 1999.
7 W. Walter, "AnalysisI", zweite Auflage, Springer- Verlag, pp.103, 1990.