Open Access Open Access  Restricted Access Subscription or Fee Access

A Study of Various Machine Learning and Deep Learning Libraries/Platforms with Their Usage Perspective

Tushar Champaneria, Ketakee Nimavat, Maitrik Shah, Sunil Jardosh


Learning is a complex multi-faceted phenomenon. While we do not understand how learning happens entirely, we understand it well enough to devise models that excel at narrow domain learning. Machine learning and deep learning enable us to create models that learn and implement that learning. There is an abundance of tools that achieve the same goals in different levels of abstraction, amount of work done and flexibility to tailor learning methods. However, they are not one-trick ponies and most of the times do not prove to be suitable for all problem scenarios involving machine learning and deep learning. Often the distinction between platforms and libraries remain as: platforms provide an abstraction of the techniques and allow easy implementation of machine learning at scale whereas libraries provide methods to build tailored solutions and often will involve coding from scratch. Depending on who is building, the amount of time and resources available, a library as well as a platform can help one get to the solution. In this paper the aim, hence, is to analyze various available tools for building the models in order to make it easier to decide which tool to use for a given scenario.

Cite this Article

Tushar Champaneria, Ketakee Nimavat, Maitrik Shah et al. A Study of Various Machine Learning and Deep Learning libraries/Platforms with Their Usage Perspective. Journal of Artificial Intelligence Research & Advances. 2018; 5(3): 1–15p.


Machine learning, deep learning, libraries, platforms

Full Text:



Quinlan JR. Induction of Decision Trees. Mach. Learn. 1986; 1 (1), 81–106p.

Sutton RS. Learning to Predict by the Method of Temporal Differences. Mach. Learn. 1988; 3 (1): 9–44p.

Aha DW, Kibler DF. Noise-Tolerant Instance-Based Learning Algorithms. Proceedings of the Eleventh International Joint Conference on Artificial Intelligence (I). 1989; 66: 794–799p.

Carbonell JG, Michalski RS, Mitchell TM. An Overview of Machine Learning. In: Machine Learning. Berlin, Heidelberg: Springer; 1983; pp 3–23.

Bengio, Y. Learning Deep Architectures for AI. Found. Trends® Mach. Learn. 2009; 2 (1), 1–127p.

Vinyals O, Toshev A, Bengio S, Erhan D. Show and Tell: A Neural Image Caption Generator. Proc. IEEE Comput. Soc. Conf. Comput. Vis. Pattern Recognit. 2015; 07–12–June, pp 3156–3164.

Xu K, Ba J, Kiros R, Cho K, Courville A, Salakhutdinov R, Zemel R, Bengio Y. Show, Attend and Tell: Neural Image Caption Generation with Visual Attention. 2015.

Zhang H, Xu T, Li H, Zhang S, Wang X, Huang X, Metaxas D. StackGAN: Text to Photo-Realistic Image Synthesis with Stacked Generative Adversarial Networks. 2016.

Hundt R. Loop Recognition in C++/Java/Go/Scala. Proceedings of Scala Days 2011. 2011; 86 (2): 298–307p. Available from [accessed September 2018].

Voskoglou C. (2017). What Is the Best Programming Language for Machine Learning? [Online] Developer Economics, Towards Data Science. Available from [accessed September 2018].

Team DJD. Deeplearning4j: Open-Source Distributed Deep Learning for the JVM. Apache Softw. Found. Licens. 2 2016.

Řehůřek R, Sojka P. Gensim–Python Framework for Vector Space Modelling. NLP Centre, Fac. Informatics, Masaryk Univ. Brno, Czech Repub. 2011.

Chollet F. (2015). Keras. [Online] GitHub. Available from [accessed September 2018].

Chen T, Li M, Cmu UW, Li Y, Lin M, Wang N, Wang M, Xu B, Zhang C, Zhang Z, et al. MXNet : A Flexible and Efficient Machine Learning Library for Heterogeneous Distributed Systems arXiv : 1512 . 01274v1 [Cs. DC] 3 December 2015. 1–6.

Yu D, Huang X. Microsoft Computational Network Toolkit (CNTK). A Tutor. Given NIPS 2015 2015.

Collobert R, Kavukcuoglu K, Farabet C. Torch7: A Matlab-like Environment for Machine Learning. BigLearn, NIPS Work. 2011; 1–6p.

Agarwal A, Barham P, Brevdo E, Chen Z, Citro C, Corrado GS, Davis A, Dean J, Devin M, Ghemawat S, et al. TensorFlow: Large-Scale Machine Learning on Heterogeneous Distributed Systems. 2015.

Jia Y, Shelhamer E, Donahue J, Karayev S, Long J, Girshick R, Guadarrama S, Darrell T. Caffe: Convolutional Architecture for Fast Feature Embedding. 2014.

Bergstra J, Breuleux O, Bastien F. F, Lamblin P, Pascanu R, Desjardins G, Turian J, Warde-Farley D, Bengio Y. Theano: A CPU and GPU Math Compiler in Python. Proc. Python Sci. Comput. Conf. 2010; Scipy, 1–7p.

King DE. Dlib-Ml: A Machine Learning Toolkit. J. Mach. Learn. Res. 2009; 1755–1758p. [accessed September 2018].

Pedregosa Fabian, et al. Scikit-Learn: Machine Learning in Python. J. Mach. Learn. Res. 2825–2830p.

Pedregosa F, Weiss R, Brucher M. Scikit-Learn: Machine Learning in Python. 2011; 12: 2825–2830p.

scikit-learn: machine learning in Python—scikit-learn 0.19.0 documentation. Available from [accessed September 2018].

Curtin RR, Cline JR, Slagle NP, March WB, Ram P, Mehta NA, Gray AG. MLPACK: A Scalable C++ Machine Learning Library. Journal of Machine Learning Research 2013; 14: 801–805p.

Natural Language Toolkit. NLTK Book. Available from [accessed September 2018].

An Easy-to-Use, Easy-to-Learn Deep Learning Platform. Paddle Paddle - Train and Deploy Deep Learning at Scale. Available from [accessed September 2018].

A Flexible Framework for Neural Networks. Chainer. Available from [accessed September 2018].


Rao D, Thakur D. A Review on Image Classification Approaches and Techniques. 2016; 2 (6): 356–360p.

Lu D, Weng Q. A Survey of Image Classification Methods and Techniques for Improving Classification Performance. Int. J. Remote Sens. 2007; 28 (5): 823–870p.

Livadas C, Walsh R, Lapsley D, Strayer WT. Using Machine Learning Techniques to Identify Botnet Traffic. Proc. Conf. Local Comput. Networks, LCN 2006, No. January 2014, 967–974p.

Tsai CF, Hsu YF, Lin CY, Lin WY. Intrusion Detection by Machine Learning: A Review. Expert Syst. Appl. 2009; 36 (10): 11994–12000p.

Sommer R, Paxson V. Outside the Closed World: On Using Machine Learning for Network Intrusion Detection. 2010 IEEE Symp. Secur. Priv. 2010; 305–316p.

Puyalnithi T, Madhu Viswanatham V. Preliminary Cardiac Disease Risk Prediction Based on Medical and Behavioural Data Set Using Supervised Machine Learning Techniques. Indian J. Sci. Technol. 2016; 9 (31), 1-5p.

Ong JBS, Wang Z, Goh RSM, Yin XF, Xin X, Fu X. Understanding Natural Disasters as Risks in Supply Chain Management through Web Data Analysis. Int. J. Comput. Commun. Eng. 2015; 4 (2): 126–133p.

Terdik G, Gal Z. Advances and Practice in Internet of Things. 4th IEEE Int. Conf. Cogn. Infocommunications, Cog Info Com 2013 - Proc. 2013; 435–440p.

Allahyari M, Pouriyeh S, Assefi M, Safaei S, Trippe ED, Gutierrez JB, Kochut K. Text Summarization Techniques: A Brief Survey. 2017; 8(10), 397-405p.

Meade F. Using Robust NLP and Machine Learning. 1997.

Yi J, Nasukawa T, Bunescu R, Niblack W. Sentiment Analyzer: Extracting Sentiments about a given Topic Using Natural Language Processing Techniques. Proc. Third IEEE Int. Conf. Data Min. 2003; 1401: 427–434p.

Gupta V, Lehal GS. A Survey of Text Summarization Extractive Techniques. J. Emerg. Technol. Web Intell. 2010; 2 (3): 258–268p.

Blei DM, Edu BB, Ng AY, Edu AS, Jordan MI, Edu JB. Latent Dirichlet Allocation. J. Mach. Learn. Res. 2003; 3; 993–1022p.

Blei DM, Ng AY, Jordan MI. Latent Dirichlet Allocation. Proc. 14th Annu. Conf. Neural Inf. Process. Syst. 2001; 601–608p.

Guo X, Singh S, Lewis R, Lee H. To Improve Monte Carlo Tree Search in ATARI Games. 2015.

Ryu S. Book Review: Predictive Analytics: The Power to Predict Who Will Click, Buy, Lie or Die. Healthc. Inform. Res. 2013; 19 (1): 63p.

Isinkaye FO, Folajimi YO, Ojokoh BA. Recommendation Systems: Principles, Methods and Evaluation. Egypt. Informatics J. 2015; 16 (3): 261–273p.

Akansu AN, Malioutov D, Palomar DP, Jay E, Mandic DP. Introduction to the Issue on Financial Signal Processing and Machine Learning for Electronic Trading. IEEE J. Sel. Top. Signal Process. 2016; 10 (6): 979–981p.

Heaton JB, Polson NG, Witte JH. Deep Learning in Finance. 2016; No. February 1–20.

Amazon Machine Learning - Predictive Analytics with AWS. Available from [accessed September 2019].

Cloud Platform: Cloud Infrastructure - IBM Bluemix. Available from [accessed September 2018].

Microsoft Azure Machine Learning Studio. Available from [accessed September 2018].

Machine Learning. Microsoft Azure. Available from [accessed September 2018].

Chappel DA. Introducing Azure Machine Learning. Microsoft Azur. 2015; 17p.

Google Cloud Computing, Hosting Services & APIs Google Cloud Platform. Available from [accessed September 2018].

Alibaba Cloud. An Integrated Suite of Cloud Products, Services and Solutions. Alibaba Cloud. Available from [accessed September 2018].


  • There are currently no refbacks.