The Impact of Learning rate on Backpropagation Algorithm in Matlab

Artificial Neural Networks (ANNs) are highly interconnected. Backpropagation is a common method for training artificial neural networks to minimize the objective function. This study describes the implementation of the backpropagation algorithm. The different errors generated at the output are fed...

Full description

Bibliographic Details
Published in:Pakistan Journal of Engineering Technology & Science
Main Authors: Abdul Ghafoor Shaikh, Wajid Ali Shaikh
Format: Article
Language:English
Published: Institute of Business Management 2023-12-01
Subjects:
Online Access:https://journals.iobm.edu.pk/index.php/pjets/article/view/1014
_version_ 1848664583928020992
author Abdul Ghafoor Shaikh
Wajid Ali Shaikh
author_facet Abdul Ghafoor Shaikh
Wajid Ali Shaikh
author_sort Abdul Ghafoor Shaikh
collection DOAJ
container_title Pakistan Journal of Engineering Technology & Science
description Artificial Neural Networks (ANNs) are highly interconnected. Backpropagation is a common method for training artificial neural networks to minimize the objective function. This study describes the implementation of the backpropagation algorithm. The different errors generated at the output are fed back to the input, and the weights of the neurons are updated by different supervised learning rates, which is a generalization of the delta rule. A sigmoid function was used as the activation function. The design was simulated using MATLAB R2018a. The maximum accuracy was achieved 0.9988 with four hidden layers
format Article
id doaj-art-e5487b4bbb6f4d479fd65ab3a5cbf830
institution Directory of Open Access Journals
issn 2222-9930
2224-2333
language English
publishDate 2023-12-01
publisher Institute of Business Management
record_format Article
spelling doaj-art-e5487b4bbb6f4d479fd65ab3a5cbf8302025-10-31T00:01:23ZengInstitute of Business ManagementPakistan Journal of Engineering Technology & Science2222-99302224-23332023-12-0111210.22555/pjets.v11i2.1014The Impact of Learning rate on Backpropagation Algorithm in MatlabAbdul Ghafoor ShaikhWajid Ali Shaikh Artificial Neural Networks (ANNs) are highly interconnected. Backpropagation is a common method for training artificial neural networks to minimize the objective function. This study describes the implementation of the backpropagation algorithm. The different errors generated at the output are fed back to the input, and the weights of the neurons are updated by different supervised learning rates, which is a generalization of the delta rule. A sigmoid function was used as the activation function. The design was simulated using MATLAB R2018a. The maximum accuracy was achieved 0.9988 with four hidden layers https://journals.iobm.edu.pk/index.php/pjets/article/view/1014Artificial Neural NetworkBackpropagation AlgorithmHidden LayerSigmoid
spellingShingle Abdul Ghafoor Shaikh
Wajid Ali Shaikh
The Impact of Learning rate on Backpropagation Algorithm in Matlab
Artificial Neural Network
Backpropagation Algorithm
Hidden Layer
Sigmoid
title The Impact of Learning rate on Backpropagation Algorithm in Matlab
title_full The Impact of Learning rate on Backpropagation Algorithm in Matlab
title_fullStr The Impact of Learning rate on Backpropagation Algorithm in Matlab
title_full_unstemmed The Impact of Learning rate on Backpropagation Algorithm in Matlab
title_short The Impact of Learning rate on Backpropagation Algorithm in Matlab
title_sort impact of learning rate on backpropagation algorithm in matlab
topic Artificial Neural Network
Backpropagation Algorithm
Hidden Layer
Sigmoid
url https://journals.iobm.edu.pk/index.php/pjets/article/view/1014
work_keys_str_mv AT abdulghafoorshaikh theimpactoflearningrateonbackpropagationalgorithminmatlab
AT wajidalishaikh theimpactoflearningrateonbackpropagationalgorithminmatlab
AT abdulghafoorshaikh impactoflearningrateonbackpropagationalgorithminmatlab
AT wajidalishaikh impactoflearningrateonbackpropagationalgorithminmatlab