A Comparative Study of Popular CNN Topologies Used for Imagenet Classification

View Sample PDF

Author(s): Hmidi Alaeddine (Laboratory of Electronics and Microelectronics, Faculty of Sciences of Monastir, Monastir University, Monastir, Tunisia)and Malek Jihene (Higher Institute of Applied Sciences and Technology of Sousse, Sousse University, Sousse, Tunisia)
Copyright: 2020
Pages: 15
Source title: Deep Neural Networks for Multimodal Imaging and Biomedical Applications
Source Author(s)/Editor(s): Annamalai Suresh (Department of Computer Science and Engineering, Nehru Institute of Engineering and Technology, Coimbatore, India), R. Udendhran (Department of Computer Science and Engineering, Bharathidasan University, India)and S. Vimal (Department of Information Technology, National Engineering College (Autonomous), Kovilpatti, India)
DOI: 10.4018/978-1-7998-3591-2.ch007

Keywords: Bioinformatics / Computer Science & IT / Medical Information Science Reference / Neural Networks

Purchase

View A Comparative Study of Popular CNN Topologies Used for Imagenet Classification on the publisher's website for pricing and purchasing information.

Abstract

Deep Learning is a relatively modern area that is a very important key in various fields such as computer vision with a trend of rapid exponential growth so that data are increasing. Since the introduction of AlexNet, the evolution of image analysis, recognition, and classification have become increasingly rapid and capable of replacing conventional algorithms used in vision tasks. This study focuses on the evolution (depth, width, multiple paths) presented in deep CNN architectures that are trained on the ImageNET database. In addition, an analysis of different characteristics of existing topologies is detailed in order to extract the various strategies used to obtain better performance.

The IRMA Community

Research IRM

A Comparative Study of Popular CNN Topologies Used for Imagenet Classification

Purchase

Abstract

Related Content

IRMA Sponsors