Machine learning by multi-feature extraction using genetic algorithms

Leila S. Shafti; Eduarde Pérez

doi:10.1007/978-3-540-30498-2_25

Machine learning by multi-feature extraction using genetic algorithms

Leila S. Shafti^*, Eduarde Pérez

^*Corresponding author for this work

Computer And Information Sciences

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

1 Citation (Scopus)

Abstract

Constructive Induction methods aim to solve the problem of learning hard concepts despite complex interaction in data. We propose a new Constructive Induction method based on Genetic Algorithms with a non-algebraic representation of features. The advantage of our method to some other similar methods is that it constructs and evaluates a combination of features. Evaluating constructed features together, instead of considering them one by one, is essential when number of interacting attributes is high and there are more than one interaction in concept. Our experiments show the effectiveness of this method to learn such concepts.

Original language	English
Title of host publication	Advances in Artificial Intelligence -- IBERAMIA 2004
Subtitle of host publication	9th Ibero-American Conference on AI, Puebla, Mexico, November 22-26, 2004, Proceedings
Editors	Christian Lemaître, Carlos A. Reyes, Jesús A González
Place of Publication	Cham
Publisher	Springer
Pages	246-255
Number of pages	10
ISBN (Electronic)	9783540304982
ISBN (Print)	9783540238065
DOIs	https://doi.org/10.1007/978-3-540-30498-2_25
Publication status	Published - 18 Nov 2004
Event	9th Ibero-American Conference on AI - Puebla, Mexico Duration: 22 Nov 2004 → 26 Nov 2004

Publication series

Name	Lecture Notes in Computer Science
Volume	3315
ISSN (Print)	0302-9743
ISSN (Electronic)	1611-3349

Conference

Conference	9th Ibero-American Conference on AI
Abbreviated title	IBERAMIA 2004
Country/Territory	Mexico
City	Puebla
Period	22/11/04 → 26/11/04

Funding

This work has been partially supported by the Spanish Interdepartmental Commission for Science and Technology (CICYT), under Grant number TIC2002-1948.

Keywords

constructive induction
complex interactions
genetic algorithms
non-algebraic representation

Access to Document

10.1007/978-3-540-30498-2_25

Cite this

Shafti, L. S., & Pérez, E. (2004). Machine learning by multi-feature extraction using genetic algorithms. In C. Lemaître, C. A. Reyes, & J. A. González (Eds.), Advances in Artificial Intelligence -- IBERAMIA 2004: 9th Ibero-American Conference on AI, Puebla, Mexico, November 22-26, 2004, Proceedings (pp. 246-255). (Lecture Notes in Computer Science; Vol. 3315). Springer. https://doi.org/10.1007/978-3-540-30498-2_25

Shafti, Leila S. ; Pérez, Eduarde. / Machine learning by multi-feature extraction using genetic algorithms. Advances in Artificial Intelligence -- IBERAMIA 2004: 9th Ibero-American Conference on AI, Puebla, Mexico, November 22-26, 2004, Proceedings. editor / Christian Lemaître ; Carlos A. Reyes ; Jesús A González. Cham : Springer, 2004. pp. 246-255 (Lecture Notes in Computer Science).

@inproceedings{705806dfd926472da3684c0109aaaa73,

title = "Machine learning by multi-feature extraction using genetic algorithms",

abstract = "Constructive Induction methods aim to solve the problem of learning hard concepts despite complex interaction in data. We propose a new Constructive Induction method based on Genetic Algorithms with a non-algebraic representation of features. The advantage of our method to some other similar methods is that it constructs and evaluates a combination of features. Evaluating constructed features together, instead of considering them one by one, is essential when number of interacting attributes is high and there are more than one interaction in concept. Our experiments show the effectiveness of this method to learn such concepts.",

keywords = "constructive induction, complex interactions, genetic algorithms, non-algebraic representation",

author = "Shafti, \{Leila S.\} and Eduarde P{\'e}rez",

year = "2004",

month = nov,

day = "18",

doi = "10.1007/978-3-540-30498-2\_25",

language = "English",

isbn = "9783540238065",

series = "Lecture Notes in Computer Science",

publisher = "Springer",

pages = "246--255",

editor = "Christian Lema{\^i}tre and Reyes, \{Carlos A.\} and Gonz{\'a}lez, \{Jes{\'u}s A\}",

booktitle = "Advances in Artificial Intelligence -- IBERAMIA 2004",

address = "Switzerland",

note = "9th Ibero-American Conference on AI, IBERAMIA 2004 ; Conference date: 22-11-2004 Through 26-11-2004",

}

Shafti, LS & Pérez, E 2004, Machine learning by multi-feature extraction using genetic algorithms. in C Lemaître, CA Reyes & JA González (eds), Advances in Artificial Intelligence -- IBERAMIA 2004: 9th Ibero-American Conference on AI, Puebla, Mexico, November 22-26, 2004, Proceedings. Lecture Notes in Computer Science, vol. 3315, Springer, Cham, pp. 246-255, 9th Ibero-American Conference on AI, Puebla, Mexico, 22/11/04. https://doi.org/10.1007/978-3-540-30498-2_25

Machine learning by multi-feature extraction using genetic algorithms. / Shafti, Leila S.; Pérez, Eduarde.
Advances in Artificial Intelligence -- IBERAMIA 2004: 9th Ibero-American Conference on AI, Puebla, Mexico, November 22-26, 2004, Proceedings. ed. / Christian Lemaître; Carlos A. Reyes; Jesús A González. Cham: Springer, 2004. p. 246-255 (Lecture Notes in Computer Science; Vol. 3315).

Research output: Chapter in Book/Report/Conference proceeding › Conference contribution book

TY - GEN

T1 - Machine learning by multi-feature extraction using genetic algorithms

AU - Shafti, Leila S.

AU - Pérez, Eduarde

PY - 2004/11/18

Y1 - 2004/11/18

N2 - Constructive Induction methods aim to solve the problem of learning hard concepts despite complex interaction in data. We propose a new Constructive Induction method based on Genetic Algorithms with a non-algebraic representation of features. The advantage of our method to some other similar methods is that it constructs and evaluates a combination of features. Evaluating constructed features together, instead of considering them one by one, is essential when number of interacting attributes is high and there are more than one interaction in concept. Our experiments show the effectiveness of this method to learn such concepts.

AB - Constructive Induction methods aim to solve the problem of learning hard concepts despite complex interaction in data. We propose a new Constructive Induction method based on Genetic Algorithms with a non-algebraic representation of features. The advantage of our method to some other similar methods is that it constructs and evaluates a combination of features. Evaluating constructed features together, instead of considering them one by one, is essential when number of interacting attributes is high and there are more than one interaction in concept. Our experiments show the effectiveness of this method to learn such concepts.

KW - constructive induction

KW - complex interactions

KW - genetic algorithms

KW - non-algebraic representation

U2 - 10.1007/978-3-540-30498-2_25

DO - 10.1007/978-3-540-30498-2_25

M3 - Conference contribution book

AN - SCOPUS:22944449329

SN - 9783540238065

T3 - Lecture Notes in Computer Science

SP - 246

EP - 255

BT - Advances in Artificial Intelligence -- IBERAMIA 2004

A2 - Lemaître, Christian

A2 - Reyes, Carlos A.

A2 - González, Jesús A

PB - Springer

CY - Cham

T2 - 9th Ibero-American Conference on AI

Y2 - 22 November 2004 through 26 November 2004

ER -

Shafti LS, Pérez E. Machine learning by multi-feature extraction using genetic algorithms. In Lemaître C, Reyes CA, González JA, editors, Advances in Artificial Intelligence -- IBERAMIA 2004: 9th Ibero-American Conference on AI, Puebla, Mexico, November 22-26, 2004, Proceedings. Cham: Springer. 2004. p. 246-255. (Lecture Notes in Computer Science). doi: 10.1007/978-3-540-30498-2_25

Machine learning by multi-feature extraction using genetic algorithms

Abstract

Publication series

Conference

Funding

Keywords

Access to Document

Fingerprint

Cite this