Demystifying Deep Learning Frameworks- A Comparative Analysis

Authors:

Divyanshu Sinha,JP Pandey,Bhavesh Chauhan,

DOI NO:

https://doi.org/10.26782/jmcms.2019.02.00010

Keywords:

Deep Learning, Feedforward MLP,Keras,Tensorflow,Theano,Caffe,Deeplearning4j,Torch,

Abstract

Deep learning is a rapidly growing field of machine learning which finds the application of its methods to provide solutions to numerous problems related to computer vision, speech recognition, natural language processing, and others. This paper gives a comparative analysis of the five deep learning tools on the grounds of training time and accuracy. Evaluation includes classifying digits from the MNIST data set making use of a fully connected neural network architecture (FCNN). Here we have selected five frameworks— Torch ,Deeplearning4j, TensorFlow, Caffe & Theano (with Keras), to evaluate their performance and accuracy. In order to enhance the comparison of the frameworks, the standard MNIST data set of handwritten digits was chosen for the classification task. When working with the data set, our goal was to identify the digits (0–9) using a fully connected neural network architecture. All computations were executed on a GPU. The key metrics addressed were training speed, classification speed, and accuracy.

Refference:

I.Anuj Dutt, AashiDutt. “Handwritten Digit Recognition Using Deep Learning. ” International Journal of Advanced Research in Computer Engineering & Technology (IJARCET) Volume 6, Issue 7, July 2017.

II.Alexander K. Seewald, “On the Brittleness of Handwritten Digit Recognition Models,”ISRN Machine Vision, vol. 2012, Article ID 834127, 2012.

III.Li DengMicrosoft Research, Redmond, Washington USA. ” The MNIST Database of Handwritten Digit Images for Machine Learning Research [Best of the Web]” IEEE Signal Processing Magazine(Volume: 29,Issue: 6, Nov. 2012).

IV.Muhammad Ramzan, Shahid Mehmood Awan,Hikmat Ullah Khan , Waseem Akhtar, Ammara Zamir,Mahwish Ilyas. “A Survey on using Neural Network based Algorithms for Hand Written Digit.” International Journal of Advanced Computer Science and Applications, Vol. 9, No. 9, 2018.

V.Subhransu Maji and Jitendra Malik EECS Department University of California, Berkeley Technical Report No. UCB/EECS-2009-159 November 25, 2009http://www2.eecs.berkeley.edu/Pubs/TechRpts/2009/EECS-2009-159.pdf

Divyanshu Sinha, JP Pandey, Bhavesh Chauhan View Download