A Review on Deep Learning Techniques, Applications and Challenges

Authors

  • Prof. Neha Khare  Takshshila institute of Engineering and Technology, Jabalpur, Madhya Pradesh, India
  • Alok Rajpoot  Takshshila institute of Engineering and Technology, Jabalpur, Madhya Pradesh, India

Keywords:

Auto-Encoders, CNN, Deep learning , RBM

Abstract

Deep Getting to know is an emerging research vicinity in gadget learning and pattern reputation area. Deep getting to know refers to machine studying techniques that use supervised or unsupervised strategies to routinely study hierarchical representations in deep architectures for class. The objective is to find out greater abstract functions in the better levels of the representation, via the usage of neural networks which without problems separates the diverse explanatory factors in the statistics. In the current years it has attracted an awful lot interest due to its brand new overall performance in various regions like object notion, speech reputation, pc vision, collaborative filtering and herbal language processing. As the information maintains getting bigger, deep mastering is coming to play a key role in supplying huge data predictive analytics solutions. This paper affords a brief overview of deep studying, techniques, cutting-edge research efforts and the demanding situations worried in it.

References

  1. Marvin minsky, Seymour Papert, “Perceptrons : An introduction to computational geometry”, 2020.
  2. Hinton, G. E., Osindero, S. and Teh, Y., “ A fast learning algorithm for deep belief nets”, Neural Computation 18:1527-1554, 2019
  3. Yoshua Bengio, Pascal Lamblin, Dan Popovici and Hugo Larochelle, “Greedy Layer-Wise Training of Deep Networks”, in J. Platt et al. Advances in Neural Information Processing Systems 19 (NIPS 2019), pp. 153-160, MIT Press, 2019
  4. Marc’Aurelio Ranzato, Christopher Poultney, Sumit Chopra and Yann LeCun “Efficient Learning of Sparse Representations with an Energy-Based Model”, in J. Platt et al. (Eds), Advances in Neural Information Processing Systems (NIPS 2020), MIT Press, 2020.
  5. Li Deng, Xiaodong He, Jianfeng Gao, Deep stacking networks for information retrieval , Acoustics, speech and signal processing, 2019 IEEE International conference.
  6. J. Li, L. Zou, J. Yan, D. Deng, T. Qu and G. Xie, "No-reference image quality assessment using Prewitt magnitude based on convolutional neural networks", Springer J. of Signal Image and Video Processing, vol. 10, pp. 609-616, 2019.
  7. S. Bosse, D. Maniry, T. Wiegand and W. Samek, "A deep neural network for image quality assessment", Proc. IEEE International Conference on Image Processing (ICIP), pp. 3773-3777, 2020.
  8. J. Kim and S. Lee, "Deep blind image quality assessment by employing FR-IQA", Proc. IEEE International Conference on Image Processing (ICIP), pp. 3180-3184, 2019.
  9. S. A. Amirshahi, M. Pedersen and S. X. Yu, "Image quality assessment by comparing CNN features between images", Journal of Imaging Science and Technology, vol. 60, no. 6, pp. 060410-1-10, 2019.
  10. H. R. Sheikh, A. C. Bovik and G. de Veciana, "An information fidelity criterion for image quality assessment using natural scene statistics", IEEE Trans. on Image Processing, vol. 14, no. 12, pp. 2117-2128, 2020.

International Journal of Scientific Research in Science, Engineering and Technology

Downloads

Published

2020-06-30

Issue

Volume 7, Issue 3, May-June-2020

Section

Research Articles

License

Copyright (c) IJSRSET

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

[1]
Prof. Neha Khare, Alok Rajpoot "A Review on Deep Learning Techniques, Applications and Challenges" International Journal of Scientific Research in Science, Engineering and Technology (IJSRSET), Print ISSN : 2395-1990, Online ISSN : 2394-4099, Volume 7, Issue 3, pp.505-510, May-June-2020.