Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding
One of the essential factors that affect the performance of Artificial Neural Networks is the learning algorithm. The performance of Multilayer Feed Forward Artificial Neural Network performance in image compression using different learning algorithms is examined in this paper. Based on Gradient Des...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
School of Engineering, Taylor’s University College
2007
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/6463/1/188-_199_Mahmoud.pdf |
| _version_ | 1796875383673454592 |
|---|---|
| author | Mahmoud, Omer Anwar, Farhat Salami, Momoh Jimoh Emiyoka |
| author_facet | Mahmoud, Omer Anwar, Farhat Salami, Momoh Jimoh Emiyoka |
| author_sort | Mahmoud, Omer |
| collection | IIUM |
| description | One of the essential factors that affect the performance of Artificial Neural Networks is the learning algorithm. The performance of Multilayer Feed Forward Artificial Neural Network performance in image compression using different learning algorithms is examined in this paper. Based on Gradient Descent, Conjugate Gradient, Quasi-Newton techniques three different error back propagation algorithms have been developed for use in training two types of neural networks, a single hidden layer network and three hidden layers network. The essence of this study is to investigate the most efficient and effective training methods for use in image compression and its subsequent applications. The obtained results show that the Quasi-Newton based algorithm
has better performance as compared to the other two algorithms. |
| first_indexed | 2024-03-05T22:37:57Z |
| format | Article |
| id | oai:generic.eprints.org:6463 |
| institution | International Islamic University Malaysia |
| language | English |
| last_indexed | 2024-03-05T22:37:57Z |
| publishDate | 2007 |
| publisher | School of Engineering, Taylor’s University College |
| record_format | dspace |
| spelling | oai:generic.eprints.org:64632019-11-25T08:07:26Z http://irep.iium.edu.my/6463/ Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding Mahmoud, Omer Anwar, Farhat Salami, Momoh Jimoh Emiyoka TK7885 Computer engineering One of the essential factors that affect the performance of Artificial Neural Networks is the learning algorithm. The performance of Multilayer Feed Forward Artificial Neural Network performance in image compression using different learning algorithms is examined in this paper. Based on Gradient Descent, Conjugate Gradient, Quasi-Newton techniques three different error back propagation algorithms have been developed for use in training two types of neural networks, a single hidden layer network and three hidden layers network. The essence of this study is to investigate the most efficient and effective training methods for use in image compression and its subsequent applications. The obtained results show that the Quasi-Newton based algorithm has better performance as compared to the other two algorithms. School of Engineering, Taylor’s University College 2007-08 Article PeerReviewed application/pdf en http://irep.iium.edu.my/6463/1/188-_199_Mahmoud.pdf Mahmoud, Omer and Anwar, Farhat and Salami, Momoh Jimoh Emiyoka (2007) Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding. Journal of Engineering Science and Technology , 2 (2). pp. 188-199. ISSN 1823-4690 http://jestec.taylors.edu.my/V2Issue2.html |
| spellingShingle | TK7885 Computer engineering Mahmoud, Omer Anwar, Farhat Salami, Momoh Jimoh Emiyoka Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding |
| title | Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding
|
| title_full | Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding
|
| title_fullStr | Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding
|
| title_full_unstemmed | Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding
|
| title_short | Learning Algorithm effect on Multilayer Feed Forward Artificial Neural Network performance in image coding
|
| title_sort | learning algorithm effect on multilayer feed forward artificial neural network performance in image coding |
| topic | TK7885 Computer engineering |
| url | http://irep.iium.edu.my/6463/1/188-_199_Mahmoud.pdf |
| work_keys_str_mv | AT mahmoudomer learningalgorithmeffectonmultilayerfeedforwardartificialneuralnetworkperformanceinimagecoding AT anwarfarhat learningalgorithmeffectonmultilayerfeedforwardartificialneuralnetworkperformanceinimagecoding AT salamimomohjimohemiyoka learningalgorithmeffectonmultilayerfeedforwardartificialneuralnetworkperformanceinimagecoding |