Differential evolution for neural networks learning enhancement.
In this paper ,we use new treatment ,Differential Evolution,, Differential Evolution (DE) has been used to determine optimal value for ANN parameters such as learning rate and momentum rate and also for weight optimization. In ANN, there are many elements need to be considered, and these include the...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Anbar
2012-06-01
|
| Series: | مجلة جامعة الانبار للعلوم الصرفة |
| Subjects: | |
| Online Access: | https://juaps.uoanbar.edu.iq/article_44119_f776b9d7228fac6cea9e6d796d1fb269.pdf |
| _version_ | 1797373374124523520 |
|---|---|
| author | Abdul Sttar Ismail wdaa |
| author_facet | Abdul Sttar Ismail wdaa |
| author_sort | Abdul Sttar Ismail wdaa |
| collection | DOAJ |
| description | In this paper ,we use new treatment ,Differential Evolution,, Differential Evolution (DE) has been used to determine optimal value for ANN parameters such as learning rate and momentum rate and also for weight optimization. In ANN, there are many elements need to be considered, and these include the number of input nodes, hidden nodes, output nodes, learning rate, momentum rate, bias parameter, minimum error and activation/transfer functions. Three programs have developed; Differential Evolution Neural Network (DENN), Genetic Algorithm Neural Network (GANN) and Particle Swarm Optimization with Neural Network (PSONN) to probe the impact of these methods on ANN learning using various datasets. The results have revealed that DENN has given quite promising results in terms of convergence rate and smaller errors compared to PSONN and GANN. |
| first_indexed | 2024-03-08T18:49:34Z |
| format | Article |
| id | doaj.art-e8c8b3083d1546468ecfa20dee056dbc |
| institution | Directory Open Access Journal |
| issn | 1991-8941 2706-6703 |
| language | English |
| last_indexed | 2024-03-08T18:49:34Z |
| publishDate | 2012-06-01 |
| publisher | University of Anbar |
| record_format | Article |
| series | مجلة جامعة الانبار للعلوم الصرفة |
| spelling | doaj.art-e8c8b3083d1546468ecfa20dee056dbc2023-12-28T21:55:39ZengUniversity of Anbarمجلة جامعة الانبار للعلوم الصرفة1991-89412706-67032012-06-0152798410.37652/juaps.2011.4411944119Differential evolution for neural networks learning enhancement.Abdul Sttar Ismail wdaa0College of Education for pure sciences- University of AnbarIn this paper ,we use new treatment ,Differential Evolution,, Differential Evolution (DE) has been used to determine optimal value for ANN parameters such as learning rate and momentum rate and also for weight optimization. In ANN, there are many elements need to be considered, and these include the number of input nodes, hidden nodes, output nodes, learning rate, momentum rate, bias parameter, minimum error and activation/transfer functions. Three programs have developed; Differential Evolution Neural Network (DENN), Genetic Algorithm Neural Network (GANN) and Particle Swarm Optimization with Neural Network (PSONN) to probe the impact of these methods on ANN learning using various datasets. The results have revealed that DENN has given quite promising results in terms of convergence rate and smaller errors compared to PSONN and GANN.https://juaps.uoanbar.edu.iq/article_44119_f776b9d7228fac6cea9e6d796d1fb269.pdfdifferential evolutionneural networkslearning enhancement |
| spellingShingle | Abdul Sttar Ismail wdaa Differential evolution for neural networks learning enhancement. مجلة جامعة الانبار للعلوم الصرفة differential evolution neural networks learning enhancement |
| title | Differential evolution for neural networks learning enhancement. |
| title_full | Differential evolution for neural networks learning enhancement. |
| title_fullStr | Differential evolution for neural networks learning enhancement. |
| title_full_unstemmed | Differential evolution for neural networks learning enhancement. |
| title_short | Differential evolution for neural networks learning enhancement. |
| title_sort | differential evolution for neural networks learning enhancement |
| topic | differential evolution neural networks learning enhancement |
| url | https://juaps.uoanbar.edu.iq/article_44119_f776b9d7228fac6cea9e6d796d1fb269.pdf |
| work_keys_str_mv | AT abdulsttarismailwdaa differentialevolutionforneuralnetworkslearningenhancement |