When the result of proposed only one πm neuron model that is not required any training stage and hidden layer is compared with the other approaches, it shows satisfactory performance.
📌 3 Maddede Bu Makale
🎯
Amaç & Hipotez: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 (πm) neuron or McCulloch-Pitts neuron model is proposed.
📊
Temel Bulgular & Veri:Since M2 problem is similar to N-bit parity problem, translated multiplicative (πt) neuron model is modified for M2 problem.
💡
Sonuç & Katkı:When the result of proposed only one πm neuron model that is not required any training stage and hidden layer is compared with the other approaches, it shows satisfactory performance.
🔬Tür:Modelleme & Sayısal Simülasyon
📍Kapsam:Genişletilmiş Akademik Örneklem
⚙️Değişkenler:Machine learning · Modified translated multiplicative neuron model · Monk’s and Balloon problems
Abstract
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 (πm) neuron or McCulloch-Pitts neuron model is proposed. Since M2 problem is similar to N-bit parity problem, translated multiplicative (πt) 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 πm neuron model that is not required any training stage and hidden layer is compared with the other approaches, it shows satisfactory performance.
Özdemir, A., İNAL, M. M. (2016). Only One Neuron either N-bit Parity Rule Based Modified Translated Multiplicative or McCulloch-Pitts Models for Some Machine Learning Problems. International Journal of Intelligent Systems and Applications in Engineering, Cilt: 4 Sayı: Special Issue-1, 67–72. https://ajindex.com/articles/995942
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
Arslanov, M.Z., Ashigaliev, D.U. and Ismail, E. E.: N-bit Parity Ordered Neural Network, Neurocomputing 48 (2002), 1053-1056 [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] 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
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
Kim, K., Kim, S., Joo, Y., Oh, A.S.: Enhanced fuzzy single layer perceptron, Advances in Neural Networks, vol.3496,pp. 603-608, 2005
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
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
Schmitt, M.: On the complexity of computing and learning with multiplicative neurons, Neural Computation, vol.14(2), pp. 241-301, 2002
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
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
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
University of California, Irvine Dataset: [Online]. Available: ftp://ftp.ics.uci.edu/pub/machine-learning-databases/monks-problems/, retrieved November 16 2016
Pilgrim, R., A., “Tic-Tac-Toe: Introduction Expert Systems to Middle School Students”, Acm Sigcse Bulletin, Vol. 2