Please use this identifier to cite or link to this item:
https://elib.bsu.by/handle/123456789/158561| Title: | Deep learning with theano, torch, caffe, tensorflow, and deeplearning4J: which one is the best in speed and accuracy? |
| Authors: | Kovalev, V. Kalinovsky, A. Kovalev, S. |
| Keywords: | ЭБ БГУ::ЕСТЕСТВЕННЫЕ И ТОЧНЫЕ НАУКИ::Математика ЭБ БГУ::ОБЩЕСТВЕННЫЕ НАУКИ::Информатика ЭБ БГУ::ТЕХНИЧЕСКИЕ И ПРИКЛАДНЫЕ НАУКИ. ОТРАСЛИ ЭКОНОМИКИ::Медицина и здравоохранение |
| Issue Date: | 2016 |
| Publisher: | Minsk: Publishing Center of BSU |
| Abstract: | This paper presents results of comparative study of leading Deep Learning frameworks including Theano (with Keras wrapper), Torch, Caffe, Tensorflow, and Deeplearning4J. Detailed results of quantitative assessment of their training and predicting speed as well as resultant classification accuracy are provided. |
| URI: | http://elib.bsu.by/handle/123456789/158561 |
| Appears in Collections: | 2016. PATTERN RECOGNITION AND INFORMATION PROCESSING (PRIP’2016) |
Files in This Item:
| File | Description | Size | Format | |
|---|---|---|---|---|
| Kovalev_Kalinovsky_Kovalev.pdf | 805,06 kB | Adobe PDF | View/Open |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.