The week's pick
Random Articles
Reseach Article
Review: Comparative Analysis of Different Techniques of DL-Frameworks
| International Journal of Computer Applications |
| Foundation of Computer Science (FCS), NY, USA |
| Volume 182 - Number 14 |
| Year of Publication: 2018 |
| Authors: K. Krishna, B. Jigar, M. Vyoma |
10.5120/ijca2018917749
|
K. Krishna, B. Jigar, M. Vyoma . Review: Comparative Analysis of Different Techniques of DL-Frameworks. International Journal of Computer Applications. 182, 14 ( Sep 2018), 26-28. DOI=10.5120/ijca2018917749
Abstract
Deep learning is developed in 2006 and it is a part of machine learning and also for the artificial intelligence. Deep learning provides state of the arts solutions of various problems in areas like speech recognition and processing, neural language processing, image processing, computer vision etc. To prepare and simulate these kind of solution, there are many open source frameworks like Theano, TensorFlow, CNTK, caffe, Torchnet, Deep Learning4j are available. Theano provides comparatively better hardware performance while TensorFlow provides better visualization by dataflow graphs. In this paper TensorFlow, Theano and CNTK will be compared on the basis of model Capability, Interface, Performance, Platform support, Speed, Distributed computing, Parallel execution. The best achievable goal of this work to display the best Deep Learning framework by implementing the neural network architecture for classifying images from several datasets. In above techniques some of the parameters of TensorFlow will give better performance than the others.
References
- Dong-sheng GAO, Yan-rong ZHAO, Jing GAO and Hao WANG, “Comparison and Analysis of the OpenSourceFrameworks for Deep Learning”, 2016 International Conference on Mathematical, Computational and Statistical Sciences and Engineering (MCSSE 2016), ISBN: 978-1-60595-396-0,240,2016.
- Ali Shatnawi, Ghadeer Al-Bdour, Raffi Al-Qurran and Mahmoud Al-Ayyoub, “A Comparative Study of Open Source Deep Learning Frameworks”, 2018 9th International Conference on Information and 11Communication Systems (ICICS), IEEE,978-1-5386-4366-2/18,72,2018.
- Rub´en D. Fonnegra, Bryan Blair, Gloria M.D´ıaz, “Performance Comparison of Deep LearningFrameworks in Image Classification Problems usingConvolutional and Recurrent Networks”, IEEE, 978-1-5386-1060-2/17,2017.
- AniruddhaParvat, Jai Chavan, SiddheshKadam, Souradeep Dev, Vidhi Pathak, “A Survey ofDeep-learning Frameworks”, International Conference on Inventive Systems and Control (ICISC-2017), IEEE, 978-1-5090-4715-4/17,1,2017.
- Shaohuai Shi, Qiang Wang, Pengfei Xu, Xiaowen Chu, “Benchmarking State-of-the-Art Deep Learning Software Tools”, 2016 7th International Conference on Cloud Computing and Big Data, IEEE,978-1-5090-3555-7/16,99,2016.
- https://www.tensorflow.org for information about TensorFlow.
- https://developer.nvidia.com/deep-learning for information about CUDA support.
- https://docs.microsoft.com/en-us/cognitive-toolkit for information about CNTK.
- Alexey Kamenev, Microsoft Research “Deep Learning in Microsoft with CNTK”.
- http://deeplearning.net/software/theanofor information about theano.
- en.wikipedia.org for information about various deep learning framework.
Index Terms
Keywords