Optimization of CNN through Novel Training Strategy for Visual Classification Problems

Entropy

Obaid ur Rehman¹  Yongfeng Huang²  Sadaqat ur Rehman²  Chin-Chen Chang³  Shanshan Tu⁴  Chathura M. Sarathchandra Magurawalage⁵ 

[1] Department of Electrical Engineering, Sarhad University of Science and IT, Peshawar 25000, Pakistan;Department of Electronic Engineering, Tsinghua University, Beijing 100084, China;Department of Information Engineering and Computer Science, Feng Chia University, Taichung City 407, Taiwan;Faculty of Information Technology, Beijing University of Technology, Beijing 100022, China;School of Computer Science and Electronic Engineering, University of Essex, Colchester CO4 3SQ, UK;

关键词: CNN optimization;    image classification;    MRPROP;    training algorithm;   

DOI  :  10.3390/e20040290

来源: DOAJ

【 摘 要 】

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.

【 授权许可】

Unknown