The convergence analysis and specification of the Population-Based Incremental Learning algorithm
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
Author(s)
Related Research Unit(s)
Detail(s)
| Original language | English |
|---|---|
| Pages (from-to) | 1868-1873 |
| Journal / Publication | Neurocomputing |
| Volume | 74 |
| Issue number | 11 |
| Publication status | Published - May 2011 |
Link(s)
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) is fixed and the learning rate α 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. © 2011 Elsevier B.V.
Research Area(s)
- Convergence, Global optimum, Population-Based Incremental Learning (PBIL)
Citation Format(s)
The convergence analysis and specification of the Population-Based Incremental Learning algorithm. / Li, Helong; Kwong, Sam; Hong, Yi.
In: Neurocomputing, Vol. 74, No. 11, 05.2011, p. 1868-1873.
In: Neurocomputing, Vol. 74, No. 11, 05.2011, p. 1868-1873.
Research output: Journal Publications and Reviews › RGC 21 - Publication in refereed journal › peer-review
