Entropy Learning in Neural Network
| Autor: | Daming Shi, Abdul Wahab, Geok See Ng, Hanwant B. Singh |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2017 |
| Předmět: |
Atmospheric Science
Artificial neural network business.industry Computer science Competitive learning Management Monitoring Policy and Law Oceanography Machine learning computer.software_genre lcsh:Technology (General) Entropy (information theory) lcsh:T1-995 Artificial intelligence business lcsh:Science (General) Waste Management and Disposal computer lcsh:Q1-390 |
| Zdroj: | ASEAN Journal on Science and Technology for Development, Vol 20, Iss 3&4, Pp 307-322 (2017) |
| ISSN: | 2224-9028 0217-5460 |
| Popis: | 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. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|