Author:
Norani Nadia Athirah,Mohd Kasihmuddin Mohd Shareduwan,Mansor Mohd. Asyraf,Khurizan Noor Saifurina Nana
Abstract
In this paper, Adaline Neural Network (ADNN) has been explored to simulate the actual signal processing between input and output. One of the drawback of the conventional ADNN is the use of the non-systematic rule that defines the learning of the network. This research incorporates logic programming that consists of various prominent logical representation. These logical rules will be a symbolic rule that defines the learning mechanism of ADNN. All the mentioned logical rule are tested with different learning rate that leads to minimization of the Mean Square Error (MSE). This paper uncovered the best logical rule that could be governed in ADNN with the lowest MSE value. The thorough comparison of the performance of the ADNN was discussed based on the performance MSE. The outcome obtained from this paper will be beneficial in various field of knowledge that requires immense data processing effort such as in engineering, healthcare, marketing, and business.
Publisher
Universiti Putra Malaysia
Subject
General Earth and Planetary Sciences,General Environmental Science
Reference34 articles.
1. Abdullah, W. A. T. W. (1992). Logic programming on a neural network. International Journal of Intelligent Systems, 7(6), 513-519. doi: https://doi.org/10.1002/int.4550070604
2. Alzaeemi, S., Mansor, M. A., Kasihmuddin, M. S. M., Sathasivam, S., & Mamat, M. (2020). Radial basis function neural network for 2 satisfiability programming. Indonesian Journal of Electrical Engineering and Computer Science, 18(1), 459-469. doi: 10.11591/ijeecs.v18.i1.pp459-469
3. Asha, P., & Anuja, J. (2010). Benchmarking the competency mapping process with special reference to manufacturing industry. Retrieved November 25, 2019, from https://www.asmedu.org/incon/INCON6HRRP.pdf
4. Chen, B., Zhu, Y., & Hu, J. (2010). Mean-square convergence analysis of ADALINE training with minimum error entropy criterion. IEEE Transactions on Neural Networks, 21(7), 1168-1179. doi: 10.1109/TNN.2010.2050212
5. Goodfellow, I., Bengio, Y., & Courville, A. (2016). Deep learning. Cambridge, USA: MIT press. doi: https://doi.org/10.4258/hir.2016.22.4.351
Cited by
4 articles.
订阅此论文施引文献
订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献