Only One Neuron either N-bit Parity Rule Based Modified Translated Multiplicative or McCulloch-Pitts Models for Some Machine Learning Problems

Öz

In this study, solutions to machine learning problems such as Monk’s 2 (M₂), Balloon and Tic-Tac-Toe problems employing a single neuron dependent on rules which use either modified translated multiplicative (π_m) neuron or McCulloch-Pitts neuron model is proposed. Since M₂ problem is similar to N-bit parity problem, translated multiplicative (π_t) neuron model is modified for M₂ problem. Also, McCulloch-Pitts neuron model is used to increase classification performance. Then either πm or McCulloch-Pitts neuron model is applied to Balloon and Tic-Tac-Toe problems. When the result of proposed only one π_m neuron model that is not required any training stage and hidden layer is compared with the other approaches, it shows satisfactory performance.

Anahtar Kelimeler

• Machine learning,Modified translated multiplicative neuron model,Monk’s and Balloon problems,N-bit parity problem,Translated multiplicative neuron model

Kaynakça

1. [1] Iyoda, E. M., Nobuhara, H. and Hirota, K.: A Solution for the N-bit Parity Problem Using a Single Translated Multiplicative Neuron, Neural Processing Letters, vol.18, pp. 213-218, 2003.
2. [2] Arslanov, M.Z., Ashigaliev, D.U. and Ismail, E. E.: N-bit Parity Ordered Neural Network, Neurocomputing 48 (2002), 1053-1056
3. [3] Al-Rawi, M.: A Neural Network to Solve the Hybrid N-parity: Learning with Generalization Issues, Neurocomputing, vol.68, pp. 273-280, 2005
4. [4] Hohil, M. E., Liu, D., Smith, S. H., Solving the N-bit parity problem using neural networks, Neural Networks, vol.12, pp.1321-1323, 1999.
5. [5] Li, D., Hirasawa, K., Hu, J., Murata, J., Studying the effects on multiplication neurons for parity problem, 41st Society of Instrument and Control Engineers-SICE,2002.
6. [6] Kim, K., Kim, S., Joo, Y., Oh, A.S.: Enhanced fuzzy single layer perceptron, Advances in Neural Networks, vol.3496,pp. 603-608, 2005.
7. [7] Setino, R.: On the solution of the parity problem by a single hidden layer feedforward neural network, Neurocomputing, vol.16 (3), pp. 225-235, 1997.
8. [8] Setiono, R., Hui, L. C. K.: Some N-bit parity problems are solvable by feed-forward networks with less than n hidden units, Int. Joint Conf. on Neural Networks, 1993, pp. 305-308.

9. [9] Schmitt, M.: On the complexity of computing and learning with multiplicative neurons, Neural Computation, vol.14(2), pp. 241-301, 2002.
10. [10] Zhang, B.-T.: A Bayesian Evolutionary Approach to The Design and Learning of Heterogeneous Neural Trees, Integrated Computer-Aided Engineering, vol. 9(1), pp. 73-86, 2002.
11. [11] Bas, E., Uslu, V. R. and Egrioglu, E.: Robust learning algorithm for multiplicative neuron model artificial neural networks, Expert Systems with Applications, vol.56, pp. 80-88, 2016.
12. [12] Thrun, S.B., Bala, J., Bloedorn, E., Bratko, I., Cestnik, B., Cheng, J., De Jong, K., Dzeroski, S., Fahlman, S.E., Fisher, D., Hamann, R., Kaufman, K., Keller, S., Kononenko, I., Kreuziger, J., Michalski, R.S., Mitchell, T., Pachowicz, P., Reich, Y., Vafaie, H., Van de Welde, W., Wenzel, W., Wnek, J., and Zhang, J.: The Monk’s Problems: A Perfor. Comparison of Different Learning Algorithm, a Report, Carnegie Mellon University CMU-CS-91-197, 1991.
13. [13] University of California, Irvine Dataset: [Online]. Available: ftp://ftp.ics.uci.edu/pub/machine-learning-databases/monks-problems/, retrieved November 16 2016.
14. [14] Pilgrim, R., A., “Tic-Tac-Toe: Introduction Expert Systems to Middle School Students”, Acm Sigcse Bulletin, Vol. 27, 340–344, (1995).
15. [15] Gordon, A., “A General Algorithm for Tic-Tac-Toe Board Evaluation”, Journal of Computing Sciences in Colleges, Vol. 21, 42-46, (2006).
16. [16] Solorio, T. and Fuentes, O.: Taking Advantage of Unlabelled Data with the Ordered Classification Algorithm, ACTA, Proc. of AI and Soft Computing ASC 2002, 357-200, (2002).
17. [17] Noughts And Crosses - The oldest graphical computer game, http://www.pong-story.com/1952.htm, retrieved November 16, 2016.
18. [18] Wachsmuth, B. G., Tic-tac-toe game, http://pirate.shu.edu/~wachsmut/Teaching/CSAS1111/Assigns-CPP/assign7.html, retrieved November 17, 2016.
19. [19] Massey, B., Tic-tac-toe board evaluation, http://web.cecs.pdx.edu/~bart/cs541-fall2001/homework/3-learn.html, retrieved November 17, 2016.
20. [20] Appel, A. W., Game player programs, http://www.cs.princeton.edu/courses/archive/spr05/cos217/asgts/gameplayer/, retrieved November 16, 2016.