Next Article in Journal
Measurement-Device Independency Analysis of Continuous-Variable Quantum Digital Signature
Next Article in Special Issue
On the Reduction of Computational Complexity of Deep Convolutional Neural Networks
Previous Article in Journal
Statistical Reasoning: Choosing and Checking the Ingredients, Inferences Based on a Measure of Statistical Evidence with Some Applications
Previous Article in Special Issue
Simulation Study on the Application of the Generalized Entropy Concept in Artificial Neural Networks
Article Menu
Issue 4 (April) cover image

Export Article

Open AccessArticle
Entropy 2018, 20(4), 290;

Optimization of CNN through Novel Training Strategy for Visual Classification Problems

Department of Electronic Engineering, Tsinghua University, Beijing 100084, China
Faculty of Information Technology, Beijing University of Technology, Beijing 100022, China
Department of Electrical Engineering, Sarhad University of Science and IT, Peshawar 25000, Pakistan
School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, UK
Department of Information Engineering and Computer Science, Feng Chia University, Taichung City 407, Taiwan
Author to whom correspondence should be addressed.
Received: 31 January 2018 / Revised: 30 March 2018 / Accepted: 14 April 2018 / Published: 17 April 2018
Full-Text   |   PDF [8832 KB, uploaded 3 May 2018]   |  


The convolution neural network (CNN) has achieved state-of-the-art performance in many computer vision applications e.g., classification, recognition, detection, etc. However, the global optimization of CNN training is still a problem. Fast classification and training play a key role in the development of the CNN. We hypothesize that the smoother and optimized the training of a CNN goes, the more efficient the end result becomes. Therefore, in this paper, we implement a modified resilient backpropagation (MRPROP) algorithm to improve the convergence and efficiency of CNN training. Particularly, a tolerant band is introduced to avoid network overtraining, which is incorporated with the global best concept for weight updating criteria to allow the training algorithm of the CNN to optimize its weights more swiftly and precisely. For comparison, we present and analyze four different training algorithms for CNN along with MRPROP, i.e., resilient backpropagation (RPROP), Levenberg–Marquardt (LM), conjugate gradient (CG), and gradient descent with momentum (GDM). Experimental results showcase the merit of the proposed approach on a public face and skin dataset. View Full-Text
Keywords: CNN optimization; image classification; MRPROP; training algorithm CNN optimization; image classification; MRPROP; training algorithm

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. (CC BY 4.0).

Share & Cite This Article

MDPI and ACS Style

Rehman, S.U.; Tu, S.; Rehman, O.U.; Huang, Y.; Magurawalage, C.M.S.; Chang, C.-C. Optimization of CNN through Novel Training Strategy for Visual Classification Problems. Entropy 2018, 20, 290.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics



[Return to top]
Entropy EISSN 1099-4300 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top