Open Access Open Access  Restricted Access Subscription Access

Convolutional Neural Network and its Architectures

Radhey Shyam

Abstract


Convolutional neural network (CNN) is a type of artificial neural network (ANN) with multiple layers. From the past decades, it has been considered as a powerful classification technique as it can handle a huge amount of imagery data. It can be applied in the field of image recognition. The name CNN has been derived from the mathematical linear operation known as convolution which is performed between two matrices. CNN has multiple building blocks, for instance, convolution layers, non-linearity layers, pooling layers, and flattening followed by fully connected layers. The CNN has better performance in the machine learning applications. Particularly, the domains that use imagery data, such as computer vision, natural language processing, medical diagnosis, and robotics. This research work will present deeper insights of CNN. Furthermore, it will also highlight the parameters that are influencing its efficacy.

Keywords


Artificial neural network, convolutional neural network, machine learning, deep learning, computer vision

Full Text:

PDF

References


Lecun Y, Bengio Y. Convolutional networks for images, speech, and time-series. Cambridge: MIT Press; 1995.

Abdel-Hamid O, Deng L, Yu D. Exploring convolutional neural network structures and optimization techniques for speech recognition. In Interspeech 2013, ISCA. 2013 Aug; 3366–3370.

Shyam R, Singh YN. A taxonomy of 2D and 3D face recognition methods. In Proceedings of 1st International Conference on Signal Processing and Integrated Networks (SPIN 2014). IEEE; 2014 Feb; 749–754.

Shyam R, Singh YN. Evaluation of Eigenfaces and Fisherfaces using Bray Curtis dissimilarity metric. In Proceedings of 9th IEEE International Conference on Industrial and Information Systems (ICIIS 2014), (Gwalior, India). IEEE; 2014 Dec; 1–6.

Shyam R. Comparative analysis of distance metrics using face recognition. Research & Reviews: Discrete Mathematical Structures (RRDMS). 2021; 8(1): 1–7.

Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi F. A survey of deep neural network architectures and their applications. Neurocomputing. 2017; 234(12): 11–26.

Ni J, Chen Y, Chen Y, Zhu J, Ali D, Cao W. A survey on theories and applications for self-driving cars based on deep learning methods. Appl Sci. 2020; 10(8): 2749.

TK Y, E O, HK K, IH R, IS L, JS K. Deep learning-based smart speaker to confirm surgical sites for cataract surgeries: A pilot study. PLoS ONE. 2020; 15(4): e0231322.

Pratt H, Coenen F, Broadbent DM, Harding SP, Zheng Y. Convolutional neural networks for diabetic retinopathy. Procedia Comput Sci. 2016; 90: 200–205. 20th Conference on Medical Image Understanding and Analysis (MIUA 2016). 10. Dumoulin V, Visin F. A guide to convolution arithmetic for deep learning. arXiv:1603.07285 [stat.ML]. 2018.

Albawi S, Mohammed TA, Al-Zawi S. Understanding of a convolutional neural network. In 2017 International Conference on Engineering and Technology (ICET). 2017; 1–6.

Maitra DS, Bhattacharya U, Parui SK. CNN based common approach to handwritten character recognition of multiple scripts. In ICDAR. IEEE Computer Society, relocated from Tunis, Tunisia. 2015; 1021–1025. 13. Gazzaniga M, Ivry R, Mangun G. Cognitive Neuroscience: The Biology of the Mind. 4th Edn. USA: W. W. Norton & Company; 2012.

Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. In: Pereira F, Burges CJC, Bottou L, Weinberger KQ, editors. Advances in Neural Information Processing Systems. Vol. 25. India: Curran Associates, Inc.; 2012.

Albawi S, Mohammed TA, Al-Zawi S. Understanding of a convolutional neural network. In 2017 International Conference on Engineering and Technology (ICET). 2017; 1–6.

https://exploreai.org/p/tensorflow-cnn.

LeCun Y, Bottou L, Bengio Y, Haffner P. Gradient-based learning applied to document recognition. In Proceedings of the IEEE. 1998; 86: 2278–2324.

https://www.deeplearningbook.org/contents/convnets.html.

Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. CoRR. vol. abs/1409.1556. 2014.

Szegedy C, Liu W, Jia Y, Sermanet P, Reed S, Anguelov D, Erhan D, Vanhoucke V, Rabinovich A. Going deeper with convolutions. arXiv:1409.4842 [cs.CV]. 2014.

Shyam R, Chakraborty R. Machine learning and its dominant paradigms. Journal of Advancements in Robotics (JoARB). 2021; 8(2): 14–23.

Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. arXiv:1512.00567 [cs.CV]. 2015. 23. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. arXiv:1512.03385 [cs.CV]. 2015.

Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. AAAI'17: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence. 2017 Feb; 4278–4284.

Xie S, Girshick R, Dollar P, Tu Z, He K. Aggregated residual transformations for deep neural networks. 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 2017; 5987–5995.


Refbacks

  • There are currently no refbacks.


Copyright (c) 2021 Journal of Computer Technology & Applications