Efficient incremental induction of decision trees

Dimitrios Kalles; Tim Morris

Efficient incremental induction of decision trees

Dimitrios Kalles, Tim Morris

Research output: Contribution to journal › Article › peer-review

Abstract

This paper proposes a method to improve ID5R, an incremental TDIDT algorithm. The new method evaluates the quality of attributes selected at the nodes of a decision tree and estimates a minimum number of steps for which these attributes are guaranteed such a selection. This results in reducing overheads during incremental learning. The method is supported by theoretical analysis and experimental results. © 1996 Kluwer Academic Publishers,.

Original language	English
Pages (from-to)	231-242
Number of pages	11
Journal	Machine Learning
Volume	24
Issue number	3
Publication status	Published - 1996

Keywords

Decision tree induction
Incremental algorithm

Cite this

@article{104c5f99db0146af8733724d5aab1de6,

title = "Efficient incremental induction of decision trees",

abstract = "This paper proposes a method to improve ID5R, an incremental TDIDT algorithm. The new method evaluates the quality of attributes selected at the nodes of a decision tree and estimates a minimum number of steps for which these attributes are guaranteed such a selection. This results in reducing overheads during incremental learning. The method is supported by theoretical analysis and experimental results. {\textcopyright} 1996 Kluwer Academic Publishers,.",

keywords = "Decision tree induction, Incremental algorithm",

author = "Dimitrios Kalles and Tim Morris",

year = "1996",

language = "English",

volume = "24",

pages = "231--242",

journal = "Machine Learning",

issn = "1573-0565",

publisher = "Springer Nature",

number = "3",

}

TY - JOUR

T1 - Efficient incremental induction of decision trees

AU - Kalles, Dimitrios

AU - Morris, Tim

PY - 1996

Y1 - 1996

N2 - This paper proposes a method to improve ID5R, an incremental TDIDT algorithm. The new method evaluates the quality of attributes selected at the nodes of a decision tree and estimates a minimum number of steps for which these attributes are guaranteed such a selection. This results in reducing overheads during incremental learning. The method is supported by theoretical analysis and experimental results. © 1996 Kluwer Academic Publishers,.

AB - This paper proposes a method to improve ID5R, an incremental TDIDT algorithm. The new method evaluates the quality of attributes selected at the nodes of a decision tree and estimates a minimum number of steps for which these attributes are guaranteed such a selection. This results in reducing overheads during incremental learning. The method is supported by theoretical analysis and experimental results. © 1996 Kluwer Academic Publishers,.

KW - Decision tree induction

KW - Incremental algorithm

M3 - Article

SN - 1573-0565

VL - 24

SP - 231

EP - 242

JO - Machine Learning

JF - Machine Learning

IS - 3

ER -

Efficient incremental induction of decision trees

Abstract

Keywords

Fingerprint

Cite this