Entropy learning in neural network
In this paper, entropy term is used in the learning phase of a neural network. As learning progresses, more hidden nodes get into saturation. The early creation of such hidden nodes may impair generalisation. Hence entropy approach is proposed to dampen the early creation of such nodes. The entropy...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
ASEAN Committee on Science and Technology
2003
|
| Subjects: | |
| Online Access: | http://irep.iium.edu.my/38199/ http://irep.iium.edu.my/38199/1/ENTROPY_LEARNING_IN_NEURAL_NETWORK.pdf |
| _version_ | 1848781559468916736 |
|---|---|
| author | Geok, See Ng Shi, Daming Abdul Rahman, Abdul Wahab Singh, H. |
| author_facet | Geok, See Ng Shi, Daming Abdul Rahman, Abdul Wahab Singh, H. |
| author_sort | Geok, See Ng |
| building | IIUM Repository |
| collection | Online Access |
| description | In this paper, entropy term is used in the learning phase of a neural network. As learning progresses, more hidden nodes get into saturation. The early creation of such hidden nodes may impair generalisation. Hence entropy approach is proposed to dampen the early creation of such nodes. The entropy learning also helps to increase the importance of relevant nodes while dampening the less important nodes. At the end of learning, the less important nodes can then be eliminated to reduce the memory requirements of the neural network. |
| first_indexed | 2025-11-14T15:51:29Z |
| format | Article |
| id | iium-38199 |
| institution | International Islamic University Malaysia |
| institution_category | Local University |
| language | English |
| last_indexed | 2025-11-14T15:51:29Z |
| publishDate | 2003 |
| publisher | ASEAN Committee on Science and Technology |
| recordtype | eprints |
| repository_type | Digital Repository |
| spelling | iium-381992014-09-12T01:42:54Z http://irep.iium.edu.my/38199/ Entropy learning in neural network Geok, See Ng Shi, Daming Abdul Rahman, Abdul Wahab Singh, H. T Technology (General) In this paper, entropy term is used in the learning phase of a neural network. As learning progresses, more hidden nodes get into saturation. The early creation of such hidden nodes may impair generalisation. Hence entropy approach is proposed to dampen the early creation of such nodes. The entropy learning also helps to increase the importance of relevant nodes while dampening the less important nodes. At the end of learning, the less important nodes can then be eliminated to reduce the memory requirements of the neural network. ASEAN Committee on Science and Technology 2003 Article PeerReviewed application/pdf en http://irep.iium.edu.my/38199/1/ENTROPY_LEARNING_IN_NEURAL_NETWORK.pdf Geok, See Ng and Shi, Daming and Abdul Rahman, Abdul Wahab and Singh, H. (2003) Entropy learning in neural network. ASEAN Journal for Science and Technology Development, 20 (3&4). pp. 307-322. ISSN 0217-5460 (P), 0976-3376 (O) http://astnet.asean.org/index.php?name=Main&file=content&cid=32 |
| spellingShingle | T Technology (General) Geok, See Ng Shi, Daming Abdul Rahman, Abdul Wahab Singh, H. Entropy learning in neural network |
| title | Entropy learning in neural network |
| title_full | Entropy learning in neural network |
| title_fullStr | Entropy learning in neural network |
| title_full_unstemmed | Entropy learning in neural network |
| title_short | Entropy learning in neural network |
| title_sort | entropy learning in neural network |
| topic | T Technology (General) |
| url | http://irep.iium.edu.my/38199/ http://irep.iium.edu.my/38199/ http://irep.iium.edu.my/38199/1/ENTROPY_LEARNING_IN_NEURAL_NETWORK.pdf |