Komparasi Fungsi Aktivasi Relu Dan Tanh Pada Multilayer Perceptron

Ichsan Firmansyah, B. Herawan Hayadi

Abstract


Neural network is a popular method used in machine research, and activation functions, especially ReLu and Tanh, have a very important function in neural networks, to minimize the error value between the output layer and the target class. With variations in the number of hidden layers, as well as the number of neurons in each different hidden layer, this study analyzes 8 models to classify the Titanic's Survivor dataset. The result is that the ReLu function has a better performance than the Tanh function, seen from the average value of accuracy and precision which is higher than the Tanh activation function. The addition of the number of hidden layers has no effect on increasing the performance of the classification results, it can be seen from the decrease in the average accuracy and precision of the models that use 3 hidden layers and models that use 4 hidden layers. The highest accuracy value was obtained in the model using the ReLu activation function with 4 hidden layers and 50 neurons in each hidden layer, while the highest precision value was obtained in the model using the ReLu activation function with 4 hidden layers and 100 neurons in each hidden layer

Keywords


Hidden layer; multilayer perceptron; neuron; relu; tanh

References


I. Ariyati, Ridwansyah, and Suhardjono, “Implementasi Particle Swarm Optimization untuk Optimalisasi Data Mining Dalam Evaluasi Kinerja Asisten Dosen,” JIKO (Jurnal Inform. dan Komputer) STMIK AKAKOM, vol. 3, no. 2, pp. 70–75, 2018.

A. Wanto et al., “Forecasting the Export and Import Volume of Crude Oil, Oil Products and Gas Using ANN,” J. Phys. Conf. Ser., vol. 1255, no. 1, 2019, doi: 10.1088/1742-6596/1255/1/012016.

M. Handayani, M. Riandini, and Z. Situmorang, “Perbandingan Fungsi Optimasi Neural Network Dalam Klasifikasi Kelayakan Calon Suami,” J. Inform., vol. 9, no. 1, pp. 78–84, 2022.

M. S. Simanjuntak, Wanayumini, R. Rosnelly, and T. S. Gunawan, “The Activity Activation Function Of Multilayer Perceptron - Based Cardiac Abnormalities,” J. Mantik, vol. 4, no. 1, pp. 555–561, 2020, [Online]. Available: http://iocscience.org/ejournal/index.php/mantik/article/view/882/59.

D. Pardede, B. H. Hayadi, I. Komputer, U. P. Utama, U. Pembangunan, and P. Budi, “Kajian literatur multi layer perceptron: seberapa baik performa algoritma ini,” J. ICT Apl. Syst., vol. 1, no. 1, pp. 23–35, 2022, [Online]. Available: https://e-jurnal.rokania.ac.id/index.php/jictas/article/view/127/84.

J. Rynkiewicz, “Asymptotic statistics for multilayer perceptron with ReLU hidden units,” Neurocomputing, vol. 342, pp. 16–23, 2019, doi: 10.1016/j.neucom.2018.11.097.

J. C. Chen and Y. M. Wang, “Comparing activation functions in modeling shoreline variation using multilayer perceptron neural network,” Water (Switzerland), vol. 12, no. 5, 2020, doi: 10.3390/W12051281.

Hartono, M. Sadikin, D. M. Sari, N. Anzelina, S. Lestari, and W. Dari, “Implementation of Artifical Neural Networks with Multilayer Perceptron for Analysis of Acceptance of Permanent Lecturers,” J. Mantik, vol. 4, no. 2, pp. 1389–1396, 2020, [Online]. Available: https://iocscience.org/ejournal/index.php/mantik.

M. Fachrie and A. P. Wibowo, “Pemanfaatan Jaringan Syaraf Tiruan Untuk Memprediksi Kinerja Satpam,” JIKO (Jurnal Inform. dan Komputer), vol. 3, no. 1, p. 46, 2018, doi: 10.26798/jiko.2018.v3i1.80.

A. J. Mohammed, M. H. Arif, and A. A. Ali, “A multilayer perceptron artificial neural network approach for improving the accuracy of intrusion detection systems,” IAES Int. J. Artif. Intell., vol. 9, no. 4, pp. 609–615, 2020, doi: 10.11591/ijai.v9.i4.pp609-615.

I. Gunawan, “Optimasi Model Artificial Neural Network untuk Klasifikasi Paket Jaringan,” Simetris, vol. 14, no. 2, pp. 1–5, 2020, doi: 10.51901/simetris.v14i2.135.

B. Al-shargabi, F. Al-shami, R. S. Alkhawaldeh, and C. Information, “Enhancing Multi-Layer Perceptron for Breast Cancer Prediction,” Int. J. Adv. Sci. Technol., vol. 130, pp. 11–20, 2019.

K. Sharma, S. College, and Rajhasthan, “Classification of IRIS Dataset using Weka,” Int. J. Comput. Appl. Inf. Technol., vol. 12, no. 1, pp. 287–291, 2020.

K. F. Margolang, M. M. Siregar, S. Riyadi, and Z. Situmorang, “Analisa Distance Metric Algoritma K-Nearest Neighbor Pada Klasifikasi Kredit Macet,” J. Inf. Syst. Res., vol. 3, no. 2, pp. 118–124, 2022, doi: 10.47065/josh.v3i2.1262.




DOI: http://dx.doi.org/10.26798/jiko.v6i2.600

Article Metrics

Abstract view : 2599 times
PDF (Bahasa Indonesia) - 1054 times

Refbacks

  • There are currently no refbacks.




Copyright (c) 2022 Ichsan Firmansyah, B. Herawan Hayadi


JIKO (Jurnal Informatika dan Komputer)

Published by
Lembaga Penelitian dan Pengabdian Masyarakat
Universitas Teknologi Digital Indonesia (d.h STMIK AKAKOM)

Jl. Raya Janti (Majapahit) No. 143 Yogyakarta, 55198
Telp. (0274)486664

Website : https://www.utdi.ac.id/

e-ISSN : 2477-3964 
p-ISSN : 2477-4413