SEARCH RESULT

Year

Subject Area

Broadcast Area

Document Type

Language

1 results listed

2018 Understanding effects of hyper-parameters on learning: A comparative analysis

In this study, we analyzed the hyper-parameters which are frequently used in deep learning methods on a generated DNN. On the Fashion-MNIST dataset, we had chance to interpret the evolution of the model to the end as a result of tests performed on a low epoch number. At the end of the study, we reached a success rate of about 90 percent on the test data and showed that the selected hyper-parameters by created model were the most accurate.

International Conference on Advanced Technologies, Computer Engineering and Science
ICATCES

Yusuf Yargı Baydilli Ü. ATİLA

216 213
Subject Area: Computer Science Broadcast Area: International Type: Oral Paper Language: English