Advertisement

A Roadmap to Deep Learning: A State-of-the-Art Step Towards Machine Learning

  • Dweepna GargEmail author
  • Parth Goel
  • Gokulnath Kandaswamy
  • Amit Ganatra
  • Ketan Kotecha
Conference paper
Part of the Communications in Computer and Information Science book series (CCIS, volume 955)

Abstract

Deep learning is a new era of machine learning and belonging to the area of artificial intelligence. It has tried to mimic the working of the way the human brain does. The models of deep learning have the capability to deal with high dimensional data and perform the complicated tasks in an accurate manner with the use of graphical processing unit (GPU). Significant performance is observed to analyze images, videos, text and speech. This paper deals with the detailed comparison of various deep learning models and the area in which these various deep learning models can be applied. We also present the comparison of various deep networks of classification. The paper also describes deep learning libraries along with the platform and interface in which they can be used. The accuracy is evaluated with respect to various machine learning and deep learning models on the MNIST dataset. The evaluation shows classification on deep learning model is far better than a machine learning model.

Keywords

Deep learning Deep learning models Deep learning libraries MNIST dataset 

References

  1. 1.
  2. 2.
    Pascanu, R., Mikolov, T., Bengio, Y.: On the difficulty of training recurrent neural networks. In: 30th International Conference on Machine Learning, pp. 1310– 1318. JMLR.org, Atlanta, GA, USA (2013)Google Scholar
  3. 3.
    Abraham, A.: Artificial neural networks. In: Sydenham, Peter H., Thorn, Richard (eds.) Handbook of Measuring System Design, pp. 901–908. Wiley, London (2005)Google Scholar
  4. 4.
    Sutskever, I., Hinton, G., Taylor, G.: The recurrent temporal restricted Boltzmann machine. In: NIPS’2008, Curran Associates, Inc., pp. 1601–1608 (2009)Google Scholar
  5. 5.
    Fischer, A: Training Restricted Boltzmann Machines. KI-Künstliche Intelligenz. 29, 441–444 (2015)Google Scholar
  6. 6.
    Hinton, G.E., Simon, O., Yee-Whye, T.: A fast learning algorithm for deep belief nets. Neural Comput. 18, 1527–1554 (2006)MathSciNetCrossRefGoogle Scholar
  7. 7.
    Huang, H., Li, R., Yang, M., Lim, T., Ding, W.: Evaluation of vehicle interior sound quality using a continuous restricted Boltzmann machine-based DBN. Mech. Syst. Signal Process. 84, 245–267 (2017)CrossRefGoogle Scholar
  8. 8.
    Lecun, Y., Bottou, L., Bengio, Y., Haffner, P.: Gradient-based learning applied to document recognition. Proc. IEEE 86, 2278–2324 (1998)CrossRefGoogle Scholar
  9. 9.
    Deng, J., Dong, W., Socher, R., Li, L.-J., Li, K., Fei-Fei, L.: ImageNet: A large-scale hierarchical image database. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 248–255. Miami (2009)Google Scholar
  10. 10.
    Krizhevsky, A., Sutskever, I., Hinton, G., E.: ImageNet classification with deep convolutional neural networks. In: NIPS, pp. 110–1114 (2012)Google Scholar
  11. 11.
    Zeiler, M.D., Fergus, R.: Visualizing and understanding convolutional networks. In: Fleet, D., Pajdla, T., Schiele, B., Tuytelaars, T. (eds.) Computer Vision–ECCV 2014. LNCS, vol. 8689. Springer, Cham (2014)Google Scholar
  12. 12.
    Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)Google Scholar
  13. 13.
    Szegedy, C., Liu, W., Jia, Y., Sermanet, P., Reed, S., Anguelov, D., et al.: Going deeper with convolutions. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 1–9. Boston (2015)Google Scholar
  14. 14.
    He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770–-778. Las Vegas, NV (2016)Google Scholar
  15. 15.
    LeCun, Y., Bengio, Y., Hinton, G.E.: Deep learning. Nature 521, 436–444 (2015)CrossRefGoogle Scholar
  16. 16.
    Graves, A.: Generating Sequences With Recurrent Neural Networks, CoRR. (2013)Google Scholar
  17. 17.
    Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9, 1735–1780 (1997)CrossRefGoogle Scholar
  18. 18.
    Hinton, G.E., Zemel, R.S.: Autoencoders, minimum description length, and Helmholtz free energy. Adv. Neural. Inf. Process. Syst. 6, 3–10 (1994)Google Scholar
  19. 19.
    Socher, R., Perelygin, A., Wu, J., Chuang, J., D. Manning, C., Ng, A., et al.: Recursive deep models for semantic compositionality over a sentiment Treebank. In: Conference on Empirical Methods in Natural Language Processing (2013)Google Scholar
  20. 20.
    Abadi, M., Barham, P., Chen, J., Chen, Z., Davis, A., Dean, J., et al.: Tensorflow: A system for large-scale machine learning. In: 12th USENIX Conference on Operating Systems Design and Implementation. pp. 265–283, USENIX Association, Savannah, GA, USA (2016)Google Scholar
  21. 21.
    Keras: The Python Deep Learning library. https://keras.io/
  22. 22.
    Deeplearning4j: Open-source, Distributed Deep Learning for the JVM. https://deeplearning4j.org/index.html
  23. 23.
    Caffe| Deep Learning Framework. http://caffe.berkeleyvision.org
  24. 24.
    Bergstra, J., Bastien, F., Breuleux, O., Lamblin, P., Pascanu, R., Delalleau, O., et al.: Theano: deep learning on gpus with python. In: Neural Information Processing Systems. Big Learn workshop (2011)Google Scholar
  25. 25.
    Collobert, R., Kavukcuoglu, K., Farabet, C.: Torch7: a matlab-like environment for machine learning. In: Neural Information Processing Systems. Big Learn workshop (2011)Google Scholar
  26. 26.
    Agarwal, A., Akchurin, E., Basoglu, C., Chen, G., Cyphers, S., Droppo, J., et al.: An Introduction to Computational Networks and the Computational Network Toolkit. Microsoft Technical Report MSR-TR-2014-112 (2014)Google Scholar
  27. 27.
    The MNIST database of handwritten digits. http://yann.lecun.com/exdb/mnist
  28. 28.
    NIST Handprinted Forms and Characters Database. https://www.nist.gov/srd/nist-special-database-19

Copyright information

© Springer Nature Singapore Pte Ltd. 2019

Authors and Affiliations

  • Dweepna Garg
    • 1
    Email author
  • Parth Goel
    • 1
  • Gokulnath Kandaswamy
    • 2
  • Amit Ganatra
    • 1
  • Ketan Kotecha
    • 3
  1. 1.Devang Patel Institute of Advance Technology and Research, Charotar University of Science and TechnologyChanga, AnandIndia
  2. 2.Lovely Faculty of Technology and SciencesLovely Professional UniversityPhagwaraIndia
  3. 3.Faculty of EngineeringSymbiosis International UniversityPuneIndia

Personalised recommendations