Analysis of Combination of Kohonen Algorithm and Resilient Backpropagation in Weighting Process

 
 
 
  • Abstract
  • Keywords
  • References
  • PDF
  • Abstract


    The Kohonen algorithm is the most superior clustering algorithm in artificial neural networks compared to other clustering algorithms, and the Resilient Backpropagation (RProp) algorithm is the best algorithm in the supervised algorithm. From the results of this study, the author tries to do a research combining kohonen algorithm with RProp algorithm, where the clustering results in the kohonen algorithm will be used as the initial input process in RProp algorithm which can speed up the data processing in RProp. In this study a combination of kohonen algorithm and Resilient Backpropagation algorithm is produced, which is abbreviated as Kohorprop (Kohonen Risilient Backpropagation). From the test results, the percentage of the Kohorpor versus RProp algorithm speed with testing for 100, 500, 1,000, 5,000, 10,000 data in 10 attempts, respectively: 54.70%, 52.92%, 50.40%, 68.52%, and 78.70%. So that shows that the Kohorprop algorithm is faster than the RProp algorithm


  • Keywords


    Kohonen, Risilent Backpropagation, Kohorprop

  • References


      [1] D. Hassabis, D. Kumaran, C. Summerfield, and M. Botvinick, “Neuroscience-Inspired Artificial Intelligence,” Neuron. 2017.

      [2] Z. Ghahramani, “Probabilistic machine learning and artificial intelligence,” Nature. 2015.

      [3] A. Intelligence, “Fundamentals of Neural Networks Artificial Intelligence Fundamentals of Neural Networks Artificial Intelligence,” Fundam. Neural Networks AI Course Lect. 37 – 38, notes, slides, 2010.

      [4] P. Langley and S. Sage, “Induction of Selective Bayesian Classifiers,” Proc. Tenth Int. Conf. Uncertain. Artif. Intell., no. 1990, pp. 399–406, 1994.

      [5] T. Kohonen, “The self-organizing map,” Proc. IEEE, 1990.

      [6] J. Vesanto and E. Alhoniemi, “Clustering of the self-organizing map,” IEEE Trans. Neural Networks, 2000.

      [7] T. Kohonen, “Essentials of the self-organizing map,” Neural Networks, 2013.

      [8] J. Vesanto, J. Himberg, E. Alhoniemi, and J. Parhankangas, “Self-organizing map in Matlab : the SOM Toolbox,” Proc. Matlab DSP Conf., 1999.

      [9] H. Ritter and T. Kohonen, “Self-organizing semantic maps,” Biol. Cybern., 1989.

      [10] M. Kivelä, A. Arenas, M. Barthelemy, J. P. Gleeson, Y. Moreno, and M. A. Porter, “Multilayer networks,” J. Complex Networks, 2014.

      [11] K. C. Gupta, “Neural Network Structures,” Neural Networks RF Microw. Des., 2000.

      [12] M. Riedmiller and H. Braun, “A direct adaptive method for faster backpropagation learning: The RPROP algorithm,” in IEEE International Conference on Neural Networks - Conference Proceedings, 1993.

      [13] C. Igel and M. Hüsken, “Improving the Rprop learning algorithm,” Proc. Second Int. Symp. Neural Comput., 2000.

      [14] C. Igel, M. Toussaint, and W. Weishui, “Rprop using the natural gradient,” Trends Appl. Constr. …, 2005.

      [15] M. Riedmiller, “Rprop-description and implementation details,” 1994.

      [16] L. K. Hansen and P. Salamon, “Neural Network Ensembles,” IEEE Trans. Pattern Anal. Mach. Intell., 1990.

      [17] A. K. Jain and J. Mao, “Artificial Neural Network: A Tutorial,” Communications, 1996.

      [18] O. S. Sitompul and E. B. Nababan, “Optimization Model of K-Means Clustering Using Artificial Neural Networks to Handle Class Imbalance Problem,” IOP Conf. Ser. Mater. Sci. Eng., vol. 288, p. 012075, Jan. 2018.

      [19] H. Karimi and F. Yousefi, “Application of artificial neural network-genetic algorithm (ANN-GA) to correlation of density in nanofluids,” Fluid Phase Equilib., vol. 336, pp. 79–83, 2012.

      [20] J. Peralta, G. Gutierrez, and A. Sanchis, “Design of Artificial Neural Networks based on Genetic Algorithms to Forecast Time Series,” 2007.

      [21] N. K. Kasabov, Foundations of neural networks, fuzzy systems, and knowledge engineering. 1996.

      [22] J. J. Noon, Network Artificial Neural & Programming Using Matlab. Yogyakarta: Andi, 2009.

      [23] C. Saranya Jothi, V. Usha, and R. Nithya, “Particle swarm optimization to produce optimal solution,” Int. J. Eng. Technol., vol. 7, no. 1.7 Special Issue 7, pp. 210–216, 2018.

      [24] R. Hasan, Particle Swarm Optimization: Method and Application. Engineering Systems Division-Massachusetts Institute of Technology, 2004.


 

View

Download

Article ID: 21662
 
DOI: 10.14419/ijet.v7i3.5.21662




Copyright © 2012-2015 Science Publishing Corporation Inc. All rights reserved.