INFERENSI TINGKAT KESALAHAN DALAM JARINGAN BACKPROPAGATION BERDASARKAN LAJU PEMAHAMAN
Keywords:
backpropagation, Artificial Neural Network, training algorithm, error, Levenberg-Marquardt
Abstract
Backpropagation network as a form of Artificial Neural Network (ANN) has been widely applied to help solve problems in various areas of life, such as forecasting, diagnostics, and pattern recognition. Performance of ANN is determined by training algorithm. In back propagation network, there are 12 training algorithms that can be used. Determining the most optimal algorithm will be tested one indicator that is the resulting error. The smaller the error, the more optimal performance of the algorithm. This study inferred statistically against training algorithms in the backpropagation network based on the variation in the lr using ANOVA test. The network parameter values that used are the target error = 0.001, the maximum epoch = 10000, and variations in the value of lr are 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, and 1. Data input is given by the randomization with a variety of many neurons in the input layer, are 5, 10, and 15, and with 1 neuron in the output layer. ANOVA test using α = 5% resulted a conclusion that the LevenbergMarquardt is the most optimal training algorithm with an average MSE of 0.001001.
References
[1] S. Kusumadewi dan S. Hartati, Neuro-Fuzzy: Integrasi Sistem Fuzzy dan Jaringan Syaraf, Yogyakarta: Graha Ilmu, 2006.
[2] M.T., Jones, Artificial IntelligenceA Systems Approach, New Delhi: Infinity Science Press LLC, 2008.
[3] J.J. Siang, Jaringan Syaraf Tiruan dan Pemrogramannya Menggunakan MATLAB, Yogyakarta: ANDI, 2009.
[4] S. Kusumadewi, Membangun Jaringan Syaraf Tiruan Menggunakan MATLAB & EXCEL LINK, Yogyakarta: Graha Ilmu, 2004.
[5] Harjono dan D. Aryanto, “Application of Artificial Neural Networks to Predict Student Achievement Study”, SAINTEK, ISSN: 1411-2558, Vol. 5 No. 2, April 2009.
[6] H. Mustafidah, D. Aryanto, D.K. Hakim, “Uji Optimalisasi Algoritma Pelatihan Conjugate Gradient pada Jaringan Syaraf Tiruan” dalam Prosiding SENATEK, ISBN: 978-602-14355- 0-2 halaman B.9-1, 21 September 2013.
[7] H. Mustafidah, D.K. Hakim, S. Sugiyanto, “Tingkat Keoptimalan Algoritma Pelatihan pada Jaringan Syaraf Tiruan (Studi Kasus Prediksi Prestasi Belajar Mahasiswa)”, JUITA, ISSN: 2086-9398 Vol. II Nomor 3, halaman 159 – 166, Mei 2013.
[8] F. Wibowo, S. Sugiyanto, H. Mustafidah, “Tingkat Ketelitian Pengenalan Pola Data pada Algoritma Pelatihan Perbaikan Metode Batch Mode dalam Jaringan Syaraf Tiruan”, Jurnal Ilmiah Nasional “JUITA”, ISSN 2086-9398, Volume II No.4, halaman 259 – 264, November 2013.
[9] H. Mustafidah, S. Hartati, R. Wardoyo, A. Harjoko, “Prediction of Test Items Validity Using Artificial Neural Network”, in Proceeding International Conference on Education, Technology, and Science (NETS) 2013 University of Muhammadiyah Purwokerto, “Improving The Quality Of Education To Face The Impact Of Technology”, December 28th, 2013.
[10] T. Taniredja dan H. Mustafidah, Penelitian Kuantitatif (Sebuah Pengantar), Bandung: Alfabeta, 2011.
[11] H. Mustafidah, and Suwarsito, “Error Rate Testing of Training Algorithm in Back Propagation Network”, International Journal of Soft Computing and Engineering (IJSCE), ISSN: 2231-2307, Volume-5 Issue-4, pp. 46 – 50, September 2015.
[12] H. Mustafidah, dan Suwarsito, “Uji Keoptimalan Algoritma Pelatihan pada Jaringan Syaraf Tiruan”, dalam Prosiding Seminar Nasional SENATKOM 2015 di Padang, ISSN : 2460-4690, halaman 243-248, 23 Oktober 2015.
[2] M.T., Jones, Artificial IntelligenceA Systems Approach, New Delhi: Infinity Science Press LLC, 2008.
[3] J.J. Siang, Jaringan Syaraf Tiruan dan Pemrogramannya Menggunakan MATLAB, Yogyakarta: ANDI, 2009.
[4] S. Kusumadewi, Membangun Jaringan Syaraf Tiruan Menggunakan MATLAB & EXCEL LINK, Yogyakarta: Graha Ilmu, 2004.
[5] Harjono dan D. Aryanto, “Application of Artificial Neural Networks to Predict Student Achievement Study”, SAINTEK, ISSN: 1411-2558, Vol. 5 No. 2, April 2009.
[6] H. Mustafidah, D. Aryanto, D.K. Hakim, “Uji Optimalisasi Algoritma Pelatihan Conjugate Gradient pada Jaringan Syaraf Tiruan” dalam Prosiding SENATEK, ISBN: 978-602-14355- 0-2 halaman B.9-1, 21 September 2013.
[7] H. Mustafidah, D.K. Hakim, S. Sugiyanto, “Tingkat Keoptimalan Algoritma Pelatihan pada Jaringan Syaraf Tiruan (Studi Kasus Prediksi Prestasi Belajar Mahasiswa)”, JUITA, ISSN: 2086-9398 Vol. II Nomor 3, halaman 159 – 166, Mei 2013.
[8] F. Wibowo, S. Sugiyanto, H. Mustafidah, “Tingkat Ketelitian Pengenalan Pola Data pada Algoritma Pelatihan Perbaikan Metode Batch Mode dalam Jaringan Syaraf Tiruan”, Jurnal Ilmiah Nasional “JUITA”, ISSN 2086-9398, Volume II No.4, halaman 259 – 264, November 2013.
[9] H. Mustafidah, S. Hartati, R. Wardoyo, A. Harjoko, “Prediction of Test Items Validity Using Artificial Neural Network”, in Proceeding International Conference on Education, Technology, and Science (NETS) 2013 University of Muhammadiyah Purwokerto, “Improving The Quality Of Education To Face The Impact Of Technology”, December 28th, 2013.
[10] T. Taniredja dan H. Mustafidah, Penelitian Kuantitatif (Sebuah Pengantar), Bandung: Alfabeta, 2011.
[11] H. Mustafidah, and Suwarsito, “Error Rate Testing of Training Algorithm in Back Propagation Network”, International Journal of Soft Computing and Engineering (IJSCE), ISSN: 2231-2307, Volume-5 Issue-4, pp. 46 – 50, September 2015.
[12] H. Mustafidah, dan Suwarsito, “Uji Keoptimalan Algoritma Pelatihan pada Jaringan Syaraf Tiruan”, dalam Prosiding Seminar Nasional SENATKOM 2015 di Padang, ISSN : 2460-4690, halaman 243-248, 23 Oktober 2015.
