Decision Tree Learning

Learning to Classify with Branching Tests

"A decision tree takes as input an object or situation described by a set of properties, and outputs a yes/no decision. Decision trees therefore represent Boolean functions. Functions with a larger range of outputs can also be represented...."
- Artificial Intelligence: A Modern Approach. By Stuart Russell & Peter Norvig. Section 18.3; page 531.

Machine Learning

Contents

Vertical Tabs

Good Starting Places

Publication

Induction of decision trees

The technology for building knowledge-based systems by inductive inference from examples has
been demonstrated successfully in several practical applications. This paper summarizes an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail. Results from recent studies show ways in which the methodology can be modified to deal with information that is noisy and/or incomplete. A reported shortcoming of the basic algorithm is discussed and two means of overcoming it are compared. The paper concludes with illustrations of current research directions

Source

By Quinlan, J. R. , 1986
classic, quinlan

General Readings

Publication

C4

Source

By Quinlan, J. R. , 1993
classic
Publication

FOIL: A midterm report

Source

By Quinlan, J. R. and Cameron-Jones, R. M. , 1993
classic
Publication

Learning logical definitions from relations

Source

By Quinlan, J. R. , 1990
classic
Publication

Semi-autonomous acquisition of pattern-based knowledge

This paper has three themes: 

(1) The task of acquiring and organizing the knowledge on which to base an expert system is difficult.

(2) Inductive inference systems can be used to extract this knowledge from data.

(3) The knowledge so obtained is powerful enough to enable systems using it to compete handily with more conventional algorithm-based systems.

These themes are explored in the context of attempts to construct high-performance  programs relevant to the chess endgame king-rook versus king-knight.

Source

By Quinlan, J.R., 1982
chess, classic, expert systems

Hardware and Software

Link

AIspace: Decision Trees

These tools are for learning and exploring concepts in artificial intelligence. They were developed at the Laboratory for Computational Intelligence at the University of British Columbia under direction of Alan Mackworth and David Poole. They are part of the online resources for Artificial Intelligence: Foundations of Computational Agents. If you are teaching or learning about AI, you may use these tools under the terms of use. Feedback is welcome.

Source

By Mackworth, Alan and David Poole
apps, instruction, software

Classic Articles & Books

Pages

Publication

Semi-autonomous acquisition of pattern-based knowledge

This paper has three themes: 

(1) The task of acquiring and organizing the knowledge on which to base an expert system is difficult.

(2) Inductive inference systems can be used to extract this knowledge from data.

(3) The knowledge so obtained is powerful enough to enable systems using it to compete handily with more conventional algorithm-based systems.

These themes are explored in the context of attempts to construct high-performance  programs relevant to the chess endgame king-rook versus king-knight.

Source

By Quinlan, J.R., 1982
chess, classic, expert systems
Publication

The optimal control of partially observable Markov processes over a finite horizon

Source

By Smallwood, R. D. and Sondik, E. J. , 1973
classic
Publication

Markovian decision processes with probabilistic observation of states

Source

By Satia, J. K. and Lave, R. E. , 1973
classic
Publication

Induction of decision trees

The technology for building knowledge-based systems by inductive inference from examples has
been demonstrated successfully in several practical applications. This paper summarizes an approach to synthesizing decision trees that has been used in a variety of systems, and it describes one such system, ID3, in detail. Results from recent studies show ways in which the methodology can be modified to deal with information that is noisy and/or incomplete. A reported shortcoming of the basic algorithm is discussed and two means of overcoming it are compared. The paper concludes with illustrations of current research directions

Source

By Quinlan, J. R. , 1986
classic, quinlan
Publication

Learning logical definitions from relations

Source

By Quinlan, J. R. , 1990
classic
Publication

FOIL: A midterm report

Source

By Quinlan, J. R. and Cameron-Jones, R. M. , 1993
classic

Pages

Vertical Tabs