Developing Hopfield Neural Network For Color Image Recognition
Hopfield Neural Network (HNN) is an iterative auto-associative network which consists of a single layer of fully connected processing elements and converges to the nearest match vector. This network alters the input patterns through successive iterations until a learned vector evolves at the output....
Saved in:
| 主要作者: | |
|---|---|
| 格式: | Thesis |
| 語言: | English |
| 出版: |
2010
|
| 主題: | |
| 在線閱讀: | http://eprints.usm.my/41915/1/KUSSAY_NUGAMESH_MUTTER.pdf |
| 標簽: |
添加標簽
沒有標簽, 成為第一個標記此記錄!
|
| id |
my-usm-ep.41915 |
|---|---|
| record_format |
uketd_dc |
| spelling |
my-usm-ep.419152019-04-12T05:26:59Z Developing Hopfield Neural Network For Color Image Recognition 2010 Mutter, Kussay Nugamesh QC1 Physics (General) Hopfield Neural Network (HNN) is an iterative auto-associative network which consists of a single layer of fully connected processing elements and converges to the nearest match vector. This network alters the input patterns through successive iterations until a learned vector evolves at the output. Then the output will no longer change with successive iterations. HNN faces real problems when it deals with images of more than two colors, noisy convergence, limited capacity, and slow learning and converging according to the number of vectors and their sizes. These problems were studied and tested the proposed solutions to obtain the optimum performance of HNN and set a starting for future research. 2010 Thesis http://eprints.usm.my/41915/ http://eprints.usm.my/41915/1/KUSSAY_NUGAMESH_MUTTER.pdf application/pdf en public phd doctoral Universiti Sains Malaysia Pusat Pengajian Sains Fizik |
| institution |
Universiti Sains Malaysia |
| collection |
USM Institutional Repository |
| language |
English |
| topic |
QC1 Physics (General) |
| spellingShingle |
QC1 Physics (General) Mutter, Kussay Nugamesh Developing Hopfield Neural Network For Color Image Recognition |
| description |
Hopfield Neural Network (HNN) is an iterative auto-associative network which consists of a single layer of fully connected processing elements and converges to the nearest match vector. This network alters the input patterns through successive iterations until a learned vector evolves at the output. Then the output will no longer change with successive iterations. HNN faces real problems when it deals with images of more than two colors, noisy convergence, limited capacity, and slow learning and converging according to the number of vectors and their sizes. These problems were studied and tested the proposed solutions to obtain the optimum performance of HNN and set a starting for future research. |
| format |
Thesis |
| qualification_name |
Doctor of Philosophy (PhD.) |
| qualification_level |
Doctorate |
| author |
Mutter, Kussay Nugamesh |
| author_facet |
Mutter, Kussay Nugamesh |
| author_sort |
Mutter, Kussay Nugamesh |
| title |
Developing Hopfield Neural Network For Color Image Recognition |
| title_short |
Developing Hopfield Neural Network For Color Image Recognition |
| title_full |
Developing Hopfield Neural Network For Color Image Recognition |
| title_fullStr |
Developing Hopfield Neural Network For Color Image Recognition |
| title_full_unstemmed |
Developing Hopfield Neural Network For Color Image Recognition |
| title_sort |
developing hopfield neural network for color image recognition |
| granting_institution |
Universiti Sains Malaysia |
| granting_department |
Pusat Pengajian Sains Fizik |
| publishDate |
2010 |
| url |
http://eprints.usm.my/41915/1/KUSSAY_NUGAMESH_MUTTER.pdf |
| _version_ |
1747820995874390016 |