Performance Analysis of Deep CNN Architectures

Year : 2024 | Volume : 14 | Issue : 02 | Page : 1 8
    By

    Radhey Shyam,

  1. Professor, Department of Information Technology, Shri Ramswaroop Memorial College of Engineering & Management, Lucknow, Uttar Pradesh, India

Abstract

A Convolutional Neural Network (CNN) is an artificial neural network renowned for its remarkable ability to handle large image datasets effectively, particularly excelling in tasks such as image recognition and classification. The fundamental structure of a CNN relies on mathematical convolution operations, comprising essential components such as convolutional layers, activation functions, pooling layers, and fully connected layers. These components work synergistically to extract and learn hierarchical features from input data, enabling CNNs to achieve high accuracy in various machine learning applications. CNNs have demonstrated exceptional performance across a range of fields, including computer vision, natural language processing, medical diagnosis, autonomous driving, and robotics. This study aims to provide an in-depth exploration of CNNs, elucidating their internal mechanisms and highlighting the critical parameters that influence their efficacy and performance. Selecting the optimal CNN architecture is contingent on several factors, including dataset complexity, computational resources, and the specific requirements of the task at hand. While pre-established models like EfficientNet and ResNet have shown considerable versatility and effectiveness, it is often prudent to experiment with and fine-tune architectures to better suit specific applications and achieve optimal results. Through a comprehensive analysis, this study underscores the importance of tailored approaches in the deployment of CNNs for diverse and complex machine learning tasks.

Keywords: Artificial neural network, convolutional neural network, machine learning, computer vision

[This article belongs to Journal of Communication Engineering & Systems ]

How to cite this article:
Radhey Shyam. Performance Analysis of Deep CNN Architectures. Journal of Communication Engineering & Systems. 2024; 14(02):1-8.
How to cite this URL:
Radhey Shyam. Performance Analysis of Deep CNN Architectures. Journal of Communication Engineering & Systems. 2024; 14(02):1-8. Available from: https://journals.stmjournals.com/joces/article=2024/view=152674


References

  1. LeCun Y, Bengio Y. Convolutional networks for images, speech, and time series. The handbook of brain theory and neural networks. 1995 Apr.
  2. Abdel-Hamid O, Deng L, Yu D. Exploring convolutional neural network structures and optimization techniques for speech recognition. In Interspeech. 2013 Aug 5; 2013: 1173–5.
  3. Singh S, Jaiswal T, Shyam R, Khanna S. Evaluation of Tweet Sentiments Using NLP. In International Symposium on Intelligent Informatics 2022 Aug 31. In: Thampi SM, Mukhopadhyay J, Paprzycki M, Li K-C, editors. Singapore: Springer Nature Singapore; 2023; 225–238.
  4. Simran, S. Tandon, S. Khanna, and R. Shyam. Detection of traffic sign using CNN. Recent Trends in Parallel Computing. 2022;9(1):14–23.
  5. Shyam R, Mishra A, Kumar A, Chowdhary A, Srivastava AK. Recording of Class Attendance Using DL-Based Face Recognition Method. In International Conference on Data Science and Applications. Singapore: Springer Nature Singapore; 2023 Jul 14; 249–260.
  6. Liu W, Wang Z, Liu X, Zeng N, Liu Y, Alsaadi FE. A survey of deep neural network architectures and their applications. Neurocomputing. 2017 Apr 19; 234: 11–26.
  7. Yoo TK, Oh E, Kim HK, Ryu IH, Lee IS, Kim JS, Kim JK. Deep learning-based smart speaker to confirm surgical sites for cataract surgeries: A pilot study. PLoS one. 2020 Apr 9; 15(4): e0231322.
  8. Shyam R, Singh R. A taxonomy of machine learning techniques. J Adv Robot. 2021 Dec; 8(3):18–25.
  9. Pratt H, Coenen F, Broadbent DM, Harding SP, Zheng Y. Convolutional neural networks for diabetic retinopathy. Procedia Comput Sci. 2016 Jan 1; 90: 200–5.
  10. 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 Apr 16; 10(8): 2749.
  11. Dumoulin V, Visin F. A guide to convolution arithmetic for deep learning. arXiv preprint arXiv:1603.07285. 2016 Mar 23.
  12. Albawi S, Mohammed TA, Al-Zawi S. Understanding of a convolutional neural network. In 2017 IEEE international conference on engineering and technology (ICET). 2017 Aug 21; 1–6.
  13. Maitra DS, Bhattacharya U, Parui SK. CNN based common approach to handwritten character recognition of multiple scripts. In 2015 13th IEEE International Conference on Document Analysis and Recognition (ICDAR). 2015 Aug 23; 1021–1025.
  14. Srivastava V, Shyam R. Enhanced object detection with deep convolutional neural networks. Int J All Res Educ Sci Methods (IJARESM). 2021; 9(7): 27–36.
  15. Shyam R. Convolutional neural network and its architectures. J Comput Technol Appl. 2021; 12(2): 6–14.
  16. Ivry RB, Mangun GR. Cognitive Neuroscience: The biology of the mind. Norton; New York City; 2014.
  17. Krizhevsky A, Sutskever I, Hinton GE. Imagenet classification with deep convolutional neural networks. Communications of the ACM, 2017 My 24; Volume 60, Issue 6 Pages 84–90.
  18. Explore ai. (2015). TensorFlow – Convolutional Neural Network (CNN). Available from: https://exploreai.org/p/tensorflow-cnn.
  19. Deep learning book. (2024). ConvNets. Available from: https://www.deeplearning.org/contents/convnets.html
  20. Zhou B, Chen D, Wang X. Seat belt detection using convolutional neural network bn-alexnet. In Intelligent Computing Theories and Application: 13th International Conference, ICIC 2017, Liverpool, UK, August 7–10, 2017, Proceedings, Part I 13; Cham: Springer International Publishing. 2017; 384–395.
  21. Simonyan K, Zisserman A. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556. 2014 Sep 4.
  22. He K, Zhang X, Ren S, Sun J. Deep residual learning for image recognition. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 770–778.
  23. Szegedy C, Vanhoucke V, Ioffe S, Shlens J, Wojna Z. Rethinking the inception architecture for computer vision. In Proceedings of the IEEE conference on computer vision and pattern recognition. 2016; 2818–2826.
  24. Szegedy C, Ioffe S, Vanhoucke V, Alemi A. Inception-v4, inception-resnet and the impact of residual connections on learning. In 31st Proceedings of the AAAI conference on artificial intelligence. 2017 Feb 12; 4278–4284.
Regular Issue Subscription Review Article
Volume 14
Issue 02
Received 10/03/2024
Accepted 22/05/2024
Published 02/07/2024
455

Login


My IP

PlumX Metrics