Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
My Menu
Saved Items

Sequence Learning via Bayesian Clustering by Dynamics

Paola Sebastiani3, Marco Ramoni4 and Paul Cohen5

(3)  Department of Mathematics and Statistics, University of Massachusetts, Amherst
(4)  Knowledge Media Institute, The Open University, UK
(5)  Department of Computer Science, University of Massachusetts, Amherst
Abstract
Suppose one has a set of univariate time series generated by one or more unknown processes. The problem we wish to solve is to discover the most probable set of processes generating the data by clustering time series into groups so that the elements of each group have similar dynamics. For example, if a batch of time series represents sensory experiences of a mobile robot, clustering by dynamics might find clusters corresponding to abstractions of sensory inputs (Ramoni, Sebastiani, Cohen, Warwick, & Davis, 1999).

Fulltext Preview (Small, Large)
Image of the first page of the fulltext

References secured to subscribers.



Export this chapter
Export this chapter as RIS | Text
 
Remote Address: 38.107.191.108 • Server: mpweb21
HTTP User Agent: CCBot/1.0 (+http://www.commoncrawl.org/bot.html)