You can view the full text of this article for free using the link below.

Title: A hybrid training method of convolution neural networks using adaptive cooperative particle swarm optimiser

Authors: Genfu Xiao; Huan Liu; Weian Guo; Lei Wang

Addresses: Department of Mechanical and Electrical Technology, Jinggangshan University, Ji'an, China ' Department of Electronics and Information, Jinggangshan University, Ji'an, China ' Sino-German College of Applied Science, Tongji University, Shanghai, China ' Department of Electronics and Information, Tongji University, Shanghai, China

Abstract: For solving the problem that it is easy to fall into the local minimum in Convolution Neural Networks (CNN) training, a hybrid training algorithm based on heuristic algorithm is proposed. Firstly, an Adaptive Cooperative Particle Swarm Optimisation (ACPSO) is proposed, which uses a learning automata to adaptively divide the subpopulation of the Cooperative Particle Swarm Optimisation (CPSO), and makes the decision variables with strong coupling relationship enter the same subpopulation. Then, the connection weights of CNN are considered as elements in particles and the CNN is trained by ACPSO algorithm. The output of the ACPSO algorithm is applied as the initial weight of the BP algorithm for the purpose of speeding up the training speed of the CNN. The experimental results show that the ACPSO-BP algorithm has achieved good results, and the recognition rate of the CNN is improved. Thus it has the potential to be applied to other deep learning fields.

Keywords: CNN; convolution neural networks; CPSO; cooperative particle swarm optimisation; learning automata; BP algorithm.

DOI: 10.1504/IJWMC.2019.097418

International Journal of Wireless and Mobile Computing, 2019 Vol.16 No.1, pp.18 - 26

Received: 27 Jun 2018
Accepted: 21 Aug 2018

Published online: 16 Jan 2019 *

Full-text access for editors Access for subscribers Free access Comment on this article