Optimisation‐based training of evolutionary convolution neural network for visual classification applications. Issue 5 (30th June 2020)

• Record Type: Journal Article
• Authors: Tu, Shanshan; ur Rehman, Sadaqat; Waqas, Muhammad; Rehman, Obaid ur; Yang, Zhongliang; Ahmad, Basharat; Halim, Zahid; Zhao, Wei
• Is Part Of: IET computer vision. Volume 14:Issue 5(2020)
• Page Start: 259
• Page End: 267
• Publication Date: 2020-06-30
• Subjects: particle swarm optimisation -- optimisation -- convolutional neural nets -- image classification; optimisation-based training -- evolutionary convolution neural network -- visual classification applications -- global optimisation -- MPSO–CG -- control parameters -- improved parameters -- velocity update equation -- training CNN -- MPSO algorithm -- baseline particle swarm optimisation algorithm -- training algorithms; Computer vision -- Periodicals; Pattern recognition systems -- Periodicals; 006.37
• DOI: 10.1049/iet-cvi.2019.0506
• Languages: English
• ISSNs: 1751-9632

Abstract

Abstract : Training of the convolution neural network (CNN) is a problem of global optimisation. This study proposed a hybrid modified particle swarm optimisation (MPSO) and conjugate gradient (CG) algorithm for efficient training of CNN. The training involves MPSO–CG to avoid trapping in local minima. Particularly, improvements in the MPSO by introducing a novel approach for control parameters, improved parameters updating criteria, a novel parameter in the velocity update equation, and fusion of the CG allows handling the issues in training CNN. In this study, the authors validate the proposed MPSO algorithm on three benchmark mathematical test functions and also compared with three different variants of the baseline particle swarm optimisation algorithm. Furthermore, the performance of the proposed MPSO–CG is also compared with other training algorithms focusing on the analysis of computational cost, convergence, and accuracy based on a standard problem specific to classification applications on CIFAR‐10 dataset and face and skin detection dataset.