Earthquake classifying neural networks trained with random dynamic neighborhood PSOs

dc.contributor.author	Mohais, Arvind S.
dc.contributor.author	Mohais, Rosemarie
dc.contributor.author	Ward, Christopher
dc.contributor.author	Posthoff, Christian
dc.date.accessioned	2011-05-26T11:52:32Z
dc.date.available	2011-05-26T11:52:32Z
dc.date.issued	2011-05-26
dc.description.abstract	This paper investigates the use of Random Dynamic Neighborhoods in Particle Swarm Optimization (PSO) for the purposeof training fixed-architecture neural networks to classify a real-world data set of seismological data.Instead of the ring or fully-connected neighborhoods that are typically used with PSOs, or even more complex graph structures, this work uses directed graphs that are randomly generated using size and uniform out-degree as parameters. Furthermore, the graphs are subjected to dynamism during the course of a run, thereby allowing for varying information exchange patterns. Neighborhood re-structuring is applied with a linearly decreasing probability at each iteration. Several experimental configurations are tested on a training portion of the data set, and are ranked according to their abilities to generalize over the entire set. Comparisons are performed with standard PSOs as well as several static non-random neighborhoods.	en_US
dc.identifier.uri	https://hdl.handle.net/2139/10078
dc.language.iso	en	en_US
dc.subject	Neural Network	en_US
dc.subject	Particle swarm optimization	en_US
dc.title	Earthquake classifying neural networks trained with random dynamic neighborhood PSOs	en_US
dc.type	Article	en_US

Files

Now showing 1 - 1 of 1

Name:: random_dynamic.html
Size:: 397 B
Format:: Hypertext Markup Language
Description:: Earthquake classifying neural networks trained with random dynamic neighborhood PSOs

Now showing 1 - 1 of 1