PENENTUAN ALGORITMA PELATIHAN PADA JARINGAN BACKPROPAGATION YANG PALING OPTIMAL DITINJAU DARI KECEPATAN JARINGAN PADA MODEL NEURON 15-22-1 DAN 15-25-1

MUHAMMADI, ALMAS ELDINOVIYO JUNJUNG (2019) PENENTUAN ALGORITMA PELATIHAN PADA JARINGAN BACKPROPAGATION YANG PALING OPTIMAL DITINJAU DARI KECEPATAN JARINGAN PADA MODEL NEURON 15-22-1 DAN 15-25-1. Bachelor thesis, Universitas Muhammadiyah Purwokerto.

[img] Text
ALMAS ELDINOVIYO COVER.pdf

Download (4MB)
[img] Text
ALMAS ELDINOVIYO BAB I.pdf

Download (933kB)
[img] Text
ALMAS ELDINOVIYO BAB II.pdf

Download (1MB)
[img] Text
ALMAS ELDINOVIYO BAB III.pdf
Restricted to Repository staff only

Download (1MB)
[img] Text
ALMAS ELDINOVIYO BAB IV.pdf
Restricted to Repository staff only

Download (1MB)
[img] Text
ALMAS ELDINOVIYO BAB V.pdf
Restricted to Repository staff only

Download (917kB)
[img] Text
ALMAS ELDINOVIYO DAPUS.pdf

Download (912kB)
[img] Text
ALMAS ELDINOVIYO LAMPIRAN.pdf
Restricted to Repository staff only

Download (7MB)

Abstract

Backpropagation is a learning algorithm that exists in Artificial Neural Networks (ANN) and is much in demand to solve problems. The backpropagation algorithm is monitored and is usually used by perceptrons with many layers to change the weights connected to the neurons in the hidden layer. In the backpropagation method there are 12 training algorithms. Therefore, in this study 20 training algorithms were tested for 20 repetitions of each learning rate (lr) to get the fastest training algorithm. This study uses a mixed method, namely qualitative and quantitative methods (using ANOVA statistical test) at the level of alpha (α) = 5%. Input data uses random data with 15 neurons input 22 neurons in hidden layer and 1 output and 15 neurons 25 neurons in hidden layer 1 output using learning rate 0.01, 0.05, 0.1, 0.2, 0.3, 0.4, 0.5, 0.6, 0.7, 0.8, 0.9, 1.0. The conclusion of the research is ANOVA statistical test on neuron models 15-22-1, the most optimal algorithm is obtained in terms of network speed, namely Resilent Backpropagation (trainrp) training algorithm with an average speed of 0.0068650 at the learning rate = 0.8. Meanwhile on the neuron model 15-25-1, the most optimal algorithm was obtained in terms of network speed, namely the training algorithm Levenberg-Marquardt (trainlm) with an average speed of 0.0070500 at the learning rate = 1.

Item Type: Thesis (Bachelor)
Uncontrolled Keywords: backpropagation, speed, anova, training algorithm
Subjects: T Technology > T Technology (General)
Divisions: Fakultas Teknik > Teknik Informatika S1
Depositing User: Catur Indra H.
Date Deposited: 15 Jul 2022 03:14
Last Modified: 15 Jul 2022 03:14
URI: https://repository.ump.ac.id:80/id/eprint/12567

Actions (login required)

View Item View Item