| Article ID | Journal | Published Year | Pages | File Type |
|---|---|---|---|---|
| 410283 | Neurocomputing | 2011 | 6 Pages |
Abstract
In this paper, we investigate the global convergence properties in probability of the Population-Based Incremental Learning (PBIL) algorithm when the initial configuration p(0)p(0) is fixed and the learning rate αα is close to zero. The convergence in probability of PBIL is confirmed by the experimental results. This paper presents a meaningful discussion on how to establish a unified convergence theory of PBIL that is not affected by the population and the selected individuals.
Keywords
Related Topics
Physical Sciences and Engineering
Computer Science
Artificial Intelligence
Authors
Helong Li, Sam Kwong, Yi Hong,