A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms
Nowadays, environments are covered by lots of qualitative (inexact) data. Making proper decisions according to this qualitative data is an ultimate aim. Artificial neural networks can be adapted to the quantitative environments, since they have ability of learning. On the other hand, fuzzy logic has...
| Main Author: | |
|---|---|
| Format: | Thesis |
| Language: | English |
| Published: |
2007
|
| Subjects: | |
| Online Access: | http://eprints.utm.my/6796/ http://eprints.utm.my/6796/1/MohammadHadiMashinchiMFSKSM2007.pdf |
| _version_ | 1848891347181764608 |
|---|---|
| author | Mashinchi, Mohammad Hadi |
| author_facet | Mashinchi, Mohammad Hadi |
| author_sort | Mashinchi, Mohammad Hadi |
| building | UTeM Institutional Repository |
| collection | Online Access |
| description | Nowadays, environments are covered by lots of qualitative (inexact) data. Making proper decisions according to this qualitative data is an ultimate aim. Artificial neural networks can be adapted to the quantitative environments, since they have ability of learning. On the other hand, fuzzy logic has the power of dealing with inexact data. To get benefit of advantageous of artificial neural networks and fuzzy logic, fuzzy artificial neural networks are proposed. This hybrid soft-computing technique has the ability of learning in qualitative environments. Thus, fuzzy artificial neural networks can make qualitative decisions according to inexact data which are fed to it. Learning process of fuzzy artificial neural networks is one of the most important issues. Thus, many learning methods for feed forward fuzzy artificial neural networks are proposed. Low speed of convergence and accuracy of training have made fuzzy artificial methods inapplicable in most of problems. Thus, efficient learning method for fuzzy artificial neural networks is demandable. In this study a “genetically tuned fuzzy back propagation method based on derivation of min-max function� as new learning method has been proposed by author. The proposed learning method has resolved some of the previous shortcomings. Importance of the proposed method is that, three main benefits are reached simultaneously; it can learn from any kind of convex fuzzy numbers, accuracy of training is higher since error function is more realistic comparing to gradient based learning methods, and convergence speed is acceptable. |
| first_indexed | 2025-11-15T20:56:31Z |
| format | Thesis |
| id | utm-6796 |
| institution | Universiti Teknologi Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-15T20:56:31Z |
| publishDate | 2007 |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | utm-67962018-08-30T08:03:51Z http://eprints.utm.my/6796/ A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms Mashinchi, Mohammad Hadi QA75 Electronic computers. Computer science Nowadays, environments are covered by lots of qualitative (inexact) data. Making proper decisions according to this qualitative data is an ultimate aim. Artificial neural networks can be adapted to the quantitative environments, since they have ability of learning. On the other hand, fuzzy logic has the power of dealing with inexact data. To get benefit of advantageous of artificial neural networks and fuzzy logic, fuzzy artificial neural networks are proposed. This hybrid soft-computing technique has the ability of learning in qualitative environments. Thus, fuzzy artificial neural networks can make qualitative decisions according to inexact data which are fed to it. Learning process of fuzzy artificial neural networks is one of the most important issues. Thus, many learning methods for feed forward fuzzy artificial neural networks are proposed. Low speed of convergence and accuracy of training have made fuzzy artificial methods inapplicable in most of problems. Thus, efficient learning method for fuzzy artificial neural networks is demandable. In this study a “genetically tuned fuzzy back propagation method based on derivation of min-max function� as new learning method has been proposed by author. The proposed learning method has resolved some of the previous shortcomings. Importance of the proposed method is that, three main benefits are reached simultaneously; it can learn from any kind of convex fuzzy numbers, accuracy of training is higher since error function is more realistic comparing to gradient based learning methods, and convergence speed is acceptable. 2007-03 Thesis NonPeerReviewed application/pdf en http://eprints.utm.my/6796/1/MohammadHadiMashinchiMFSKSM2007.pdf Mashinchi, Mohammad Hadi (2007) A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms. Masters thesis, Universiti Teknologi Malaysia, Faculty of Computer Science and Information System. http://dms.library.utm.my:8080/vital/access/manager/Repository/vital:62513 |
| spellingShingle | QA75 Electronic computers. Computer science Mashinchi, Mohammad Hadi A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms |
| title | A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms |
| title_full | A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms |
| title_fullStr | A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms |
| title_full_unstemmed | A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms |
| title_short | A new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms |
| title_sort | new fuzzy back-propagation learning method based on derivation of min-max function tuned with genetic algorithms |
| topic | QA75 Electronic computers. Computer science |
| url | http://eprints.utm.my/6796/ http://eprints.utm.my/6796/ http://eprints.utm.my/6796/1/MohammadHadiMashinchiMFSKSM2007.pdf |