AdaGrad Gradient Descent Method for AI Image Management
| Autor: | Peng Yang, Jen-Kuang Fang, Wen-Long Lu, Cher-Min Fong, Chien-Wei Chang, Chao-Kai Hung |
|---|---|
| Rok vydání: | 2020 |
| Předmět: |
0209 industrial biotechnology
Computer science business.industry Generalization Deep learning ComputingMethodologies_IMAGEPROCESSINGANDCOMPUTERVISION MathematicsofComputing_NUMERICALANALYSIS 02 engineering and technology 010501 environmental sciences 01 natural sciences Image (mathematics) 020901 industrial engineering & automation Artificial intelligence business Gradient descent Algorithm 0105 earth and related environmental sciences |
| Zdroj: | ICCE-TW |
| DOI: | 10.1109/icce-taiwan49838.2020.9258085 |
| Popis: | In this study, we used AdaGrad gradient descent method in optimizer for image deep learning, and compare with Adam gradient descent methods. After processing over six thousand huge database of through silicon via images, AdaGrad has shown a fast convergence and less generalization errors than Adam. The results help Artificial Intelligence for making the management of image judgment more accurate and faster. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|