New MILP approach for pattern generation in LAD

Hong Seo Ryoo, Premnath Ayyalasomayajula

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Logical Analysis of Data (LAD) is a logic-based learning technique for extracting hidden patterns in data. Typically, term enumeration techniques are used in LAD for generating patterns of various degrees, which, in turn, are used to construct a discriminant to classify different types of data. The term enumeration techniques, however, can be impractical and need be extremely selective as the number of degree d patterns over n Boolean variables is 2 d (n d) and grows exponentially with d. In this paper, we propose a new procedure for generating patterns that sequentially solves MILPs involving n binary variables. With the advent of powerful MILP solvers, the new MILP-based procedure presents a practical and efficient way to generating patterns in LAD. In particular, the new procedure will prove useful when the dataset under study requires more complex, higher degree patterns for accurate discovery of knowledge in it. Using the proposed pattern generation procedure, we experiment with two-, three-, and four-class medical databases from the Repository of Machine Learning Databases and Domain Theories maintained by the University of California at Irvine. Experimental results demonstrate that the proposed procedure is effective - in terms of accuracy in learning - as well as efficient - in terms of CPU time required for construction of patterns and discriminant for 100% accuracy in training.

Original languageEnglish
Title of host publicationIIE Annual Conference and Exhibition 2004
Publication statusPublished - 2004 Dec 1
EventIIE Annual Conference and Exhibition 2004 - Houston, TX, United States
Duration: 2004 May 152004 May 19

Other

OtherIIE Annual Conference and Exhibition 2004
CountryUnited States
CityHouston, TX
Period04/5/1504/5/19

Fingerprint

Program processors
Learning systems
Experiments

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Ryoo, H. S., & Ayyalasomayajula, P. (2004). New MILP approach for pattern generation in LAD. In IIE Annual Conference and Exhibition 2004

New MILP approach for pattern generation in LAD. / Ryoo, Hong Seo; Ayyalasomayajula, Premnath.

IIE Annual Conference and Exhibition 2004. 2004.

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Ryoo, HS & Ayyalasomayajula, P 2004, New MILP approach for pattern generation in LAD. in IIE Annual Conference and Exhibition 2004. IIE Annual Conference and Exhibition 2004, Houston, TX, United States, 04/5/15.
Ryoo HS, Ayyalasomayajula P. New MILP approach for pattern generation in LAD. In IIE Annual Conference and Exhibition 2004. 2004
Ryoo, Hong Seo ; Ayyalasomayajula, Premnath. / New MILP approach for pattern generation in LAD. IIE Annual Conference and Exhibition 2004. 2004.
@inproceedings{e54a72f23a994b99b26a057f4efc437d,
title = "New MILP approach for pattern generation in LAD",
abstract = "Logical Analysis of Data (LAD) is a logic-based learning technique for extracting hidden patterns in data. Typically, term enumeration techniques are used in LAD for generating patterns of various degrees, which, in turn, are used to construct a discriminant to classify different types of data. The term enumeration techniques, however, can be impractical and need be extremely selective as the number of degree d patterns over n Boolean variables is 2 d (n d) and grows exponentially with d. In this paper, we propose a new procedure for generating patterns that sequentially solves MILPs involving n binary variables. With the advent of powerful MILP solvers, the new MILP-based procedure presents a practical and efficient way to generating patterns in LAD. In particular, the new procedure will prove useful when the dataset under study requires more complex, higher degree patterns for accurate discovery of knowledge in it. Using the proposed pattern generation procedure, we experiment with two-, three-, and four-class medical databases from the Repository of Machine Learning Databases and Domain Theories maintained by the University of California at Irvine. Experimental results demonstrate that the proposed procedure is effective - in terms of accuracy in learning - as well as efficient - in terms of CPU time required for construction of patterns and discriminant for 100{\%} accuracy in training.",
author = "Ryoo, {Hong Seo} and Premnath Ayyalasomayajula",
year = "2004",
month = "12",
day = "1",
language = "English",
booktitle = "IIE Annual Conference and Exhibition 2004",

}

TY - GEN

T1 - New MILP approach for pattern generation in LAD

AU - Ryoo, Hong Seo

AU - Ayyalasomayajula, Premnath

PY - 2004/12/1

Y1 - 2004/12/1

N2 - Logical Analysis of Data (LAD) is a logic-based learning technique for extracting hidden patterns in data. Typically, term enumeration techniques are used in LAD for generating patterns of various degrees, which, in turn, are used to construct a discriminant to classify different types of data. The term enumeration techniques, however, can be impractical and need be extremely selective as the number of degree d patterns over n Boolean variables is 2 d (n d) and grows exponentially with d. In this paper, we propose a new procedure for generating patterns that sequentially solves MILPs involving n binary variables. With the advent of powerful MILP solvers, the new MILP-based procedure presents a practical and efficient way to generating patterns in LAD. In particular, the new procedure will prove useful when the dataset under study requires more complex, higher degree patterns for accurate discovery of knowledge in it. Using the proposed pattern generation procedure, we experiment with two-, three-, and four-class medical databases from the Repository of Machine Learning Databases and Domain Theories maintained by the University of California at Irvine. Experimental results demonstrate that the proposed procedure is effective - in terms of accuracy in learning - as well as efficient - in terms of CPU time required for construction of patterns and discriminant for 100% accuracy in training.

AB - Logical Analysis of Data (LAD) is a logic-based learning technique for extracting hidden patterns in data. Typically, term enumeration techniques are used in LAD for generating patterns of various degrees, which, in turn, are used to construct a discriminant to classify different types of data. The term enumeration techniques, however, can be impractical and need be extremely selective as the number of degree d patterns over n Boolean variables is 2 d (n d) and grows exponentially with d. In this paper, we propose a new procedure for generating patterns that sequentially solves MILPs involving n binary variables. With the advent of powerful MILP solvers, the new MILP-based procedure presents a practical and efficient way to generating patterns in LAD. In particular, the new procedure will prove useful when the dataset under study requires more complex, higher degree patterns for accurate discovery of knowledge in it. Using the proposed pattern generation procedure, we experiment with two-, three-, and four-class medical databases from the Repository of Machine Learning Databases and Domain Theories maintained by the University of California at Irvine. Experimental results demonstrate that the proposed procedure is effective - in terms of accuracy in learning - as well as efficient - in terms of CPU time required for construction of patterns and discriminant for 100% accuracy in training.

UR - http://www.scopus.com/inward/record.url?scp=30044439129&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=30044439129&partnerID=8YFLogxK

M3 - Conference contribution

AN - SCOPUS:30044439129

BT - IIE Annual Conference and Exhibition 2004

ER -