Artificial Intelligent Systems and Machine Learning

Open Access Open Access  Restricted Access Subscription Access
Open Access Open Access Open Access  Restricted Access Restricted Access Subscription Access

A Comprehensive Survey on Convolutional Neural Networks .


Affiliations
1 no, India
     

   Subscribe/Renew Journal


Convolutional Neural Networks (CNN) is a unique category of Neural Network that has displayed promising results in Computer Vision and Image Processing. Computer Vision problems heavily depend on the features of the input data and the process of extracting those features. CNN provides a novel way of extracting those features with the help of filters and automatically learning them. CNN‟s are also used in a broad spectrum of applications, including but not limited to Image Classification, Image Segmentation, Object Detection, Speech Recognition, and others. This paper focuses on the comprehensive analysis of CNN components, types of activation functions, regularization techniques, and a brief study of the different CNN architectures.

Keywords

Convolution Neural Network, GoogLeNet, ResNet, MobileNet.
User
Subscription Login to verify subscription
Notifications
Font Size

  • LeCun, Y., Bengio, Y. & Hinton, G. Deep learning. Nature 521, 436–444, May 2015.

  • R. M. Prakash, N. Thenmoezhi and M. Gayathri, "Face Recognition with Convolutional Neural Network and Transfer Learning," 2019 International Conference on Smart Systems and Inventive Technology (ICSSIT), Tirunelveli, India, 2019, pp. 861-864.

  • Farabet, C. Couprie, L. Najman, and Y. LeCun, "Learning Hierarchical Features for Scene Labeling," in IEEE Transactions on Pattern Analysis and Machine Intelligence, vol. 35, no. 8, pp. 1915-1929, Aug. 2013.

  • Toshev and C. Szegedy, "DeepPose: Human Pose Estimation via Deep Neural Networks," 2014 IEEE Conference on Computer Vision and Pattern Recognition, Columbus, OH, 2014, pp. 1653-1660.

  • Jaderberg, M., Vedaldi, A., & Zisserman, A. Deep Features for Text Spotting. Lecture Notes in Computer Science, 512–528, 2014.

  • J. Huang, J. Li, and Y. Gong, "An analysis of convolutional neural networks for speech recognition," 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), Brisbane, QLD, 2015, pp. 4989-4993.

  • Ashwin Bhandare et al, Applications of Convolutional Neural Networks, IJCSIT, 2016.

  • Lindsay, Grace W. “Convolutional Neural Networks as a Model of the Visual System: Past, Present, and Future.” Journal of Cognitive Neuroscience, 1-15, 2020.

  • LeCun Y, Boser B, Denker JS, et al. Backpropagation applied to handwritten zip code recognition. Neural Comput 1:541–551, 1989.

  • LeCun Y, Bottou L, Bengio Y, Haffner P Gradient-based learning applied to document recognition. Proc IEEE 86: 2278–2324, 1998.

  • Krizhevsky, Alex, Ilya Sutskever, and Geoffrey E. Hinton. "Imagenet classification with deep convolutional neural networks." Advances in neural information processing systems, vol 25, Jan 2012.

  • Szegedy et al., "Going deeper with convolutions," 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), 2015, pp. 1-9.

  • Karen Simonyan and Andrew Zisserman. "Very deep convolutional

  • networks for large-scale image recognition." arXiv preprint

  • arXiv:1409.1556, 2014.

  • He, Kaiming, et al. "Deep residual learning for image recognition."

  • arXiv preprint arXiv:1512.03385, 2015.

  • Huang, G., Liu, Z., & Weinberger, K.Q. Densely Connected

  • Convolutional Networks. 2017 IEEE Conference on Computer Vision

  • and Pattern Recognition (CVPR), 2261-2269, 2017.

  • Nitish Srivastava, Geoffrey Hinton, Alex Krizhevsky, Ilya Sutskever,

  • and Ruslan Salakhutdinov. 2014. Dropout: a simple way to prevent

  • neural networks from overfitting. J. Mach. Learn. Res. 15, 1 (January

  • , 1929–1958.

  • Devries, T., & Taylor, G.W. Improved Regularization of Convolutional

  • Neural Networks with Cutout. ArXiv, abs/1708.04552, 2017.

  • Howard, A., Zhu, M., Chen, B., Kalenichenko, D., Wang, W., Weyand, T., Andreetto, M., & Adam, H. MobileNets: Efficient Convolutional Neural Networks for Mobile Vision Applications. ArXiv, abs/1704.04861, 2017.

  • Li, Z., Yang, W., Peng, S., & Liu, F. A Survey of Convolutional Neural Networks: Analysis, Applications, and Prospects. ArXiv, abs/2004.02806, 2020.

  • Sumit Saha, 2018, Dec 15, A comprehensive guide to convolutional neural network.

  • Available: https://towardsdatascience.com/a-comprehensive-guide-toconvolutiona l-neural-networks-the-eli5-way-3bd2b1164a53

  • David Frossard, 2016, Jun 17 Available: https://www.cs.toronto.edu/~frossard/post/vgg16/

  • Chi Feng Wang, 2018, Aug 14. Available: https://towardsdatascience.com/a-basic-introduction-to-separable-convo lutions-b99ec3102728 .


Abstract Views: 191

PDF Views: 0




  • A Comprehensive Survey on Convolutional Neural Networks .

Abstract Views: 191  |  PDF Views: 0

Authors

C. Abhishek
no, India
Vineeta
no, India

Abstract


Convolutional Neural Networks (CNN) is a unique category of Neural Network that has displayed promising results in Computer Vision and Image Processing. Computer Vision problems heavily depend on the features of the input data and the process of extracting those features. CNN provides a novel way of extracting those features with the help of filters and automatically learning them. CNN‟s are also used in a broad spectrum of applications, including but not limited to Image Classification, Image Segmentation, Object Detection, Speech Recognition, and others. This paper focuses on the comprehensive analysis of CNN components, types of activation functions, regularization techniques, and a brief study of the different CNN architectures.

Keywords


Convolution Neural Network, GoogLeNet, ResNet, MobileNet.

References