Optimisation‐based training of evolutionary convolution neural network for visual classification applications

Optimisation‐based training of evolutionary convolution neural network for visual classification applications

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. Particu...

Full description

Bibliographic Details
Main Authors: Shanshan Tu, Sadaqat urRehman, Muhammad Waqas, Obaid ur Rehman, Zhongliang Yang, Basharat Ahmad, Zahid Halim, Wei Zhao
Format: Article
Language:English
Published: Wiley 2020-08-01
Series:IET Computer Vision
Subjects:
optimisation-based training
evolutionary convolution neural network
visual classification applications
global optimisation
MPSO–CG
control parameters
Online Access:https://doi.org/10.1049/iet-cvi.2019.0506

Internet

https://doi.org/10.1049/iet-cvi.2019.0506

Similar Items