International Journal of Science and Research (IJSR)

International Journal of Science and Research (IJSR)
Since Year 2012 | Open Access | Fully Refereed | Peer Reviewed

ISSN: 2319-7064




Downloads: 0

Review Papers | Computer Science | India | Volume 11 Issue 7, July 2022


A Comparative Review of Recent Architectures of Convolutional Neural Networks

Kalpana Devi [2] | Aman Kumar Sharma


Abstract: A Deep Convolutional Neural Network (CNN) is an important part of deep learning that has delivered admirable successes in various competitions related to Image Processing and Computer Vision. Certain attractive application fields of CNN vary from Image and Video Recognition, Image Segmentation and Classification, Medical Image Analysis, Natural Language Processing, and Object detection. One of the greatest powerful abilities of deep CNN is the various feature extraction in an automatic way. Recently, developments in the research of CNNs and attractive deep CNN architectures have been described due to the inherence of the huge quantity of data and refinement in hardware automation. A handful of encouraging concepts such as the use of distinct activation and loss functions, regularization, parameters optimization, and architecture modernization, derive progress in deep CNNs. However, the remarkable advancement in the representational ability of the deep CNN is accomplished by architectural modernization. Thus, this review paper presents a brief survey of the advances that can occur in the architecture of CNNs from the very first architecture to the recent one. This paper, therefore, targets the inherent anatomy in the newly disclosed deep CNNs architectures and accordingly describes the strengths and gaps of various deep CNNs architectures.


Keywords: Deep Learning, Convolutional Neural Networks, Anatomy, Representational Capacity, Residual Learning, and Channel Boosted CNN


Edition: Volume 11 Issue 7, July 2022,


Pages: 1263 - 1270


How to Cite this Article?

Kalpana Devi, Aman Kumar Sharma, "A Comparative Review of Recent Architectures of Convolutional Neural Networks", International Journal of Science and Research (IJSR), Volume 11 Issue 7, July 2022, pp. 1263-1270, https://www.ijsr.net/get_abstract.php?paper_id=SR22717131601

How to Share this Article?

Enter Your Email Address




Similar Articles with Keyword 'Deep Learning'

Downloads: 190 | Weekly Hits: ⮙1 | Monthly Hits: ⮙2

Research Paper, Computer Science, United States of America, Volume 9 Issue 9, September 2020

Pages: 1095 - 1100

Maintaining Social Distancing using Artificial Intelligence

Krish Chaudhary

Share this Article

Downloads: 1

Review Papers, Computer Science, Saudi Arabia, Volume 11 Issue 2, February 2022

Pages: 854 - 860

Rumor Detection Using Machine Learning in Social Media: A Survey

Afnan Alsadhan | Monirah Al-Ajlan | Mehmet Sabih Aksoy [2]

Share this Article


Top