An efficient fuzzy optimization algorithm based on convolutional neural network
| Autor: | Tao Li, Liu Wenzhou, Mengqi Nie, Gaihua Wang |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2020 |
| Předmět: |
network weights
0209 industrial biotechnology Optimization algorithm Computer science business.industry convolutional neural network Pattern recognition optimization algorithm 02 engineering and technology Engineering (General). Civil engineering (General) Convolutional neural network Fuzzy logic 020901 industrial engineering & automation Feature (computer vision) 0202 electrical engineering electronic engineering information engineering 020201 artificial intelligence & image processing Artificial intelligence TA1-2040 business fuzzy membership |
| Zdroj: | MATEC Web of Conferences, Vol 309, p 03002 (2020) |
| Popis: | The paper proposes a method based on dense-sparse-dense optimization algorithm. It uses sparsity to tune network weights. By adding fuzzy membership, the optimization strategy can enhance the feature information with larger weights and weaken the feature information with less weight. Through accurate cutting of network weights, parameters in network are effectively reduced. The experimental results show that the performance of this method is better than the existing method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|