Improving generalization in backpropagation networks architectures
This paper gives a prototype recognizer that uses rough reduction module to find the optimal representation for backpropagation networks. The proposed approach exhibits a hybrid methodology for feedforward neural networks and rough set theory. The system is a two stand alone subsystems, in which the...
| Main Authors: | , , |
|---|---|
| Format: | Conference or Workshop Item |
| Language: | English |
| Published: |
2005
|
| Online Access: | http://psasir.upm.edu.my/id/eprint/38992/1/38992.pdf |
| _version_ | 1796973451770068992 |
|---|---|
| author | Ali Adlan, Hanan Hassan Ramli, Abd Rahman Mohd Babiker, Elsadig Ahmed |
| author_facet | Ali Adlan, Hanan Hassan Ramli, Abd Rahman Mohd Babiker, Elsadig Ahmed |
| author_sort | Ali Adlan, Hanan Hassan |
| collection | UPM |
| description | This paper gives a prototype recognizer that uses rough reduction module to find the optimal representation for backpropagation networks. The proposed approach exhibits a hybrid methodology for feedforward neural networks and rough set theory. The system is a two stand alone subsystems, in which the output of the first is fed to the second for recognition tasks. The system is investigated for detection and recognition of patterns present in an image. The rough module deals with uncertainty and irrelevant observations inherited in the data. The novel architecture integrates the two approaches to recognize pattern efficiently, with minimal neurons architecture. |
| first_indexed | 2024-03-06T08:42:51Z |
| format | Conference or Workshop Item |
| id | upm.eprints-38992 |
| institution | Universiti Putra Malaysia |
| language | English |
| last_indexed | 2024-03-06T08:42:51Z |
| publishDate | 2005 |
| record_format | dspace |
| spelling | upm.eprints-389922015-07-13T07:14:49Z http://psasir.upm.edu.my/id/eprint/38992/ Improving generalization in backpropagation networks architectures Ali Adlan, Hanan Hassan Ramli, Abd Rahman Mohd Babiker, Elsadig Ahmed This paper gives a prototype recognizer that uses rough reduction module to find the optimal representation for backpropagation networks. The proposed approach exhibits a hybrid methodology for feedforward neural networks and rough set theory. The system is a two stand alone subsystems, in which the output of the first is fed to the second for recognition tasks. The system is investigated for detection and recognition of patterns present in an image. The rough module deals with uncertainty and irrelevant observations inherited in the data. The novel architecture integrates the two approaches to recognize pattern efficiently, with minimal neurons architecture. 2005 Conference or Workshop Item NonPeerReviewed application/pdf en http://psasir.upm.edu.my/id/eprint/38992/1/38992.pdf Ali Adlan, Hanan Hassan and Ramli, Abd Rahman and Mohd Babiker, Elsadig Ahmed (2005) Improving generalization in backpropagation networks architectures. In: International Advanced Technology Congress: Conference on Intelligent Systems and Robotics, 6-8 Dec. 2005, Putrajaya, Malaysia. . |
| spellingShingle | Ali Adlan, Hanan Hassan Ramli, Abd Rahman Mohd Babiker, Elsadig Ahmed Improving generalization in backpropagation networks architectures |
| title | Improving generalization in backpropagation networks architectures |
| title_full | Improving generalization in backpropagation networks architectures |
| title_fullStr | Improving generalization in backpropagation networks architectures |
| title_full_unstemmed | Improving generalization in backpropagation networks architectures |
| title_short | Improving generalization in backpropagation networks architectures |
| title_sort | improving generalization in backpropagation networks architectures |
| url | http://psasir.upm.edu.my/id/eprint/38992/1/38992.pdf |
| work_keys_str_mv | AT aliadlanhananhassan improvinggeneralizationinbackpropagationnetworksarchitectures AT ramliabdrahman improvinggeneralizationinbackpropagationnetworksarchitectures AT mohdbabikerelsadigahmed improvinggeneralizationinbackpropagationnetworksarchitectures |