Contour Gradient Optimization

Zhou Wu, Shi Cheng, Yuhui ShiAdvances 2020 · DOI · OpenAlex

Abstract

Inspired by local cooperation in the real world, a new evolutionary algorithm, Contour Gradient Optimization algorithm (CGO), is proposed for solving optimization problems. CGO is a new type of population-based algorithm that emulates the cooperation among neighbors. Each individual in CGO evolves in its neighborhood environment to find a better region. Each individual moves with a velocity measured by the field of its nearest individuals. The field includes the attractive forces from its better neighbor in the higher contour level and the repulsive force from its worse neighbor in the lower contour level. In this chapter, CGO is compared with six different widely used optimization algorithms, and comparative analysis shows that CGO is better than these algorithms in respect of accuracy and effectiveness.
BibTeX
@inproceedings{wu2020contour,
  author = {Zhou Wu and Shi Cheng and Yuhui Shi},
  title = {{Contour Gradient Optimization}},
  booktitle = {Advances},
  year = {2020},
  doi = {10.4018/978-1-7998-3222-5.ch012},
}

Loading related content...

Figure