A CONVblock for Convolutional Neural Networks

View Sample PDF

Author(s): Hmidi Alaeddine (Laboratory of Electronics and Microelectronics, Faculty of Sciences of Monastir, Monastir University, Tunisia)and Malek Jihene (Higher Institute of Applied Sciences and Technology of Sousse, Sousse University, Tunisia & Laboratory of Electronics and Microelectronics, Faculty of Sciences of Monastir, Monastir University, Tunisia)
Copyright: 2021
Pages: 14
Source title: Deep Learning Applications in Medical Imaging
Source Author(s)/Editor(s): Sanjay Saxena (International Institute of Information Technology, India)and Sudip Paul (North-Eastern Hill University, India)
DOI: 10.4018/978-1-7998-5071-7.ch004

Keywords: Knowledge Management and Library Science / Machine Learning / Medical Information Science Reference / Medical Technologies

Purchase

View A CONVblock for Convolutional Neural Networks on the publisher's website for pricing and purchasing information.

Abstract

The reduction in the size of convolution filters has been shown to be effective in image classification models. They make it possible to reduce the calculation and the number of parameters used in the operations of the convolution layer while increasing the efficiency of the representation. The authors present a deep architecture for classification with improved performance. The main objective of this architecture is to improve the main performances of the network thanks to a new design based on CONVblock. The proposal is evaluated on a classification database: CIFAR-10 and MNIST. The experimental results demonstrate the effectiveness of the proposed method. This architecture offers an error of 1.4% on CIFAR-10 and 0.055% on MNIST.

The IRMA Community

Research IRM

A CONVblock for Convolutional Neural Networks

Purchase

Abstract

Related Content

IRMA Sponsors