Heuristic Search Based Stacking of Classifiers. Ledezma, A., Aler, R., & Borrajo, D. Abbass, H. A., Sarker, R., & Newton, C., editors. Data Mining: a Heuristic Approach, pages 54–67. Idea Group Publishing, 2001. abstract bibtex Currently, the combination of several classifiers is one of the most active fields within inductive learning. Examples of such techniques are boost- ing, bagging and stacking. From these three techniques, stacking is perhaps the least used one. One of the main reasons for this relates to the difficulty to define and parameterize its components: selecting which combination of base classifiers to use, and which classifiers to use as the meta-classifier. The approach we present in this chapter poses this problem as an optimization task, and then uses optimization techniques based on heuristic search to solve it. In particular, we apply genetic algorithms to automatically obtain the ideal combination of learning methods for the stacking system.
@INBOOK{gastacking-heuristic01,
chapter = {Heuristic Search Based Stacking of Classifiers},
pages = {54--67},
title = {Data Mining: a Heuristic Approach},
publisher = {Idea Group Publishing},
year = {2001},
editor = {Hussein A. Abbass and Ruhul Sarker and Charles Newton},
author = {Agapito Ledezma and Ricardo Aler and Daniel Borrajo},
abstract = {Currently, the combination of several classifiers is one of the most
active
fields within inductive learning. Examples of such techniques are
boost-
ing, bagging and stacking. From these three techniques, stacking is
perhaps the least used one. One of the main reasons for this relates
to the
difficulty to define and parameterize its components: selecting which
combination of base classifiers to use, and which classifiers to use
as the
meta-classifier. The approach we present in this chapter poses this
problem as an optimization task, and then uses optimization techniques
based on heuristic search to solve it. In particular, we apply genetic
algorithms to automatically obtain the ideal combination of learning
methods for the stacking system.},
bib2html_pubtype = {Book Chapter},
bib2html_rescat = {Ensemble of Classifiers},
isbn = {1-930708-26-2},
key = {conjuntos},
owner = {ledezma},
timestamp = {2011.11.21}
}
Downloads: 0
{"_id":{"_str":"5342a9600e946d920a002f7b"},"__v":1,"authorIDs":[],"author_short":["Ledezma, A.","Aler, R.","Borrajo, D."],"bibbaseid":"ledezma-aler-borrajo-dataminingaheuristicapproach-2001","bibdata":{"bibtype":"inbook","type":"inbook","chapter":"Heuristic Search Based Stacking of Classifiers","pages":"54–67","title":"Data Mining: a Heuristic Approach","publisher":"Idea Group Publishing","year":"2001","editor":[{"firstnames":["Hussein","A."],"propositions":[],"lastnames":["Abbass"],"suffixes":[]},{"firstnames":["Ruhul"],"propositions":[],"lastnames":["Sarker"],"suffixes":[]},{"firstnames":["Charles"],"propositions":[],"lastnames":["Newton"],"suffixes":[]}],"author":[{"firstnames":["Agapito"],"propositions":[],"lastnames":["Ledezma"],"suffixes":[]},{"firstnames":["Ricardo"],"propositions":[],"lastnames":["Aler"],"suffixes":[]},{"firstnames":["Daniel"],"propositions":[],"lastnames":["Borrajo"],"suffixes":[]}],"abstract":"Currently, the combination of several classifiers is one of the most active fields within inductive learning. Examples of such techniques are boost- ing, bagging and stacking. From these three techniques, stacking is perhaps the least used one. One of the main reasons for this relates to the difficulty to define and parameterize its components: selecting which combination of base classifiers to use, and which classifiers to use as the meta-classifier. The approach we present in this chapter poses this problem as an optimization task, and then uses optimization techniques based on heuristic search to solve it. In particular, we apply genetic algorithms to automatically obtain the ideal combination of learning methods for the stacking system.","bib2html_pubtype":"Book Chapter","bib2html_rescat":"Ensemble of Classifiers","isbn":"1-930708-26-2","key":"gastacking-heuristic01","owner":"ledezma","timestamp":"2011.11.21","bibtex":"@INBOOK{gastacking-heuristic01,\r\n chapter = {Heuristic Search Based Stacking of Classifiers},\r\n pages = {54--67},\r\n title = {Data Mining: a Heuristic Approach},\r\n publisher = {Idea Group Publishing},\r\n year = {2001},\r\n editor = {Hussein A. Abbass and Ruhul Sarker and Charles Newton},\r\n author = {Agapito Ledezma and Ricardo Aler and Daniel Borrajo},\r\n abstract = {Currently, the combination of several classifiers is one of the most\r\n\tactive\r\n\t\r\n\tfields within inductive learning. Examples of such techniques are\r\n\tboost-\r\n\t\r\n\ting, bagging and stacking. From these three techniques, stacking is\r\n\t\r\n\tperhaps the least used one. One of the main reasons for this relates\r\n\tto the\r\n\t\r\n\tdifficulty to define and parameterize its components: selecting which\r\n\t\r\n\tcombination of base classifiers to use, and which classifiers to use\r\n\tas the\r\n\t\r\n\tmeta-classifier. The approach we present in this chapter poses this\r\n\t\r\n\tproblem as an optimization task, and then uses optimization techniques\r\n\t\r\n\tbased on heuristic search to solve it. In particular, we apply genetic\r\n\t\r\n\talgorithms to automatically obtain the ideal combination of learning\r\n\t\r\n\tmethods for the stacking system.},\r\n bib2html_pubtype = {Book Chapter},\r\n bib2html_rescat = {Ensemble of Classifiers},\r\n isbn = {1-930708-26-2},\r\n key = {conjuntos},\r\n owner = {ledezma},\r\n timestamp = {2011.11.21}\r\n}\r\n\r\n","author_short":["Ledezma, A.","Aler, R.","Borrajo, D."],"editor_short":["Abbass, H. A.","Sarker, R.","Newton, C."],"id":"gastacking-heuristic01","bibbaseid":"ledezma-aler-borrajo-dataminingaheuristicapproach-2001","role":"author","urls":{},"downloads":0,"html":"","metadata":{"authorlinks":{}}},"bibtype":"inbook","biburl":"http://www.caos.inf.uc3m.es/bibs/pubCAOS.bib","downloads":0,"keywords":[],"search_terms":["data","mining","heuristic","approach","ledezma","aler","borrajo"],"title":"Data Mining: a Heuristic Approach","year":2001,"dataSources":["Z4T4fewybNpYCWveD"]}