Optimasi Nilai Bobot Algoritma Backpropagation Neural Network Dengan Algoritma Genetika

Moh. Dasuki

Abstract


Backprogation Neural Network (BPNN) merupakan salah satu metode peramalan yang sudah banyak dilakukan kemampuan Artificial Neural Network dalam melakukan suatu pembelajaran terbukti mempunyai kinerja yang cukup baik, namun Backpropagation memiliki dua kelemahan utama yaitu kecepatan convergence yang buruk dan tidak stabil, hal ini disebabkan karena resiko terjebaknya pada lokal minimum. Dua kelemahan itu dipengaruhi bobot awal yang dipilih secara random. Algoritma Genetika akan digunakan untuk menentukan bobot serta bias awal terhadap parameter Backpropagation sehingga bisa mendapatkan kemampuan belajar yang baik. Hasil yang diperoleh dari hasil experiment yang sudah dilakukan menggunakan Jaringan Syaraf Tiruan yang di optimasi menggunakan Algoritma Genetika menghasilkan nilai Root Mean Sequare Error yang lebih baik dibandingkan dengan Jaringan Syaraf Tiruan tampa optimasi.

Keywords


Backprogation Neural Network, Genetic Algorithm

References


Abhishek, Kumar, Abhay Kumar, Rajeev Ranjan, and Sarthak Kumar. 2012. “A Rainfall Prediction Model Using Artificial Neural Network.” Proceedings - 2012 IEEE Control and System Graduate Research Colloquium, ICSGRC 2012, no. Icsgrc: 82–87. https://doi.org/10.1109/ICSGRC.2012.6287140.

Burse, Kavita, Manish Manoria, and Vishnu Pratap Singh Kirar. 2011. “Improved Back Propagation Algorithm to Avoid Local Minima in Multiplicative Neuron Model.” Communications in Computer and Information Science 147 CCIS (12): 67–73. https://doi.org/10.1007/978-3-642-20573-6_11.

Cui, Dapeng, and David Curry. 2005. “Prediction in Marketing Using the Support Vector Machine.” Marketing Science 24 (4): 595–615. https://doi.org/10.1287/mksc.1050.0123.

Ding, Shifei, Chunyang Su, and Junzhao Yu. 2011. “An Optimizing BP Neural Network Algorithm Based on Genetic Algorithm.” Artificial Intelligence Review 36 (2): 153–62. https://doi.org/10.1007/s10462-011-9208-z.

Habib, Md. 2013. “An Empirical Approach to Optimize Design of Backpropagation Neural Network Classifier for Textile Defect Inspection.” British Journal of Mathematics & Computer Science 3 (4): 617–34. https://doi.org/10.9734/bjmcs/2013/4154.

Lee, Charles W. 1997. “Training Feedforward Neural Networks: An Algorithm Giving Improved Generalization.” Neural Networks 10 (1): 61–68. https://doi.org/10.1016/S0893-6080(96)00071-8.

Nawi, Nazri Mohd, Abdullah Khan, and Mohammad Zubair Rehman. 2013. “A New Back-Propagation Neural Network Optimized.” Iccsa 2013, 413–26.

Nikelshpur, Dmitry, and Charles Tappert. 2013. “Using Particle Swarm Optimization to Pre-Train Artificial Neural Networks : Selecting Initial Training Weights for Feed-Forward Back-Propagation Neural Networks.” Proceedings of Student-Faculty Research Day, 1–7.

Sexton, Randall S., and Naheel A. Sikander. 2001. “Data Mining Using a Genetic Algorithm-Trained Neural Network.” International Journal of Intelligent Systems in Accounting, Finance & Management 10 (4): 201–10. https://doi.org/10.1002/isaf.205.

Siregar, Muhammad Noor Hasan. 2017. “Neural Network Analysis With Backpropogation In Predicting Human Development Index (HDI) Component by Regency/City In North Sumatera.” IJISTECH (International Journal Of Information System & Technology) 1 (1): 22. https://doi.org/10.30645/ijistech.v1i1.3.

Wanto, Anjar. 2018. “Penerapan Jaringan Saraf Tiruan Dalam Memprediksi Jumlah Kemiskinan Pada Kabupaten/Kota Di Provinsi Riau.” Klik - Kumpulan Jurnal Ilmu Komputer 5 (1): 61. https://doi.org/10.20527/klik.v5i1.129.




DOI: https://doi.org/10.32528/justindo.v6i1.5280

Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Moh. Dasuki

Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

View My Stats