Center for Machine Learning and Intelligent Systems
About  Citation Policy  Donate a Data Set  Contact


Repository Web            Google
View ALL Data Sets

DGP2 - The Second Data Generation Program Data Set
Download: Data Folder, Data Set Description

Abstract: Generates application domains based on specific parameters, number of features, and proportion of positive to negative examples

Data Set Characteristics:  

Data-Generator

Number of Instances:

N/A

Area:

N/A

Attribute Characteristics:

Real

Number of Attributes:

N/A

Date Donated

N/A

Associated Tasks:

N/A

Missing Values?

N/A

Number of Web Hits:

15810


Source:

Powell Benedict
University of Illinois at Urbana
Inductive Learning Group
Beckman Institute
Urbana, IL 61801
tel: (217) 244-1620
E-mail: benedict '@' cs.uiuc.edu


Data Set Information:

DGP/2 is an improvement of DGP. It allows for additional parameters and automates the setting of the standard deviation parameter, which is not easily done by the user. In particular, DGP/2 allows for variation in the number of instances, the number of features, the range of feature values, the number of peaks, the percent of positive instances desired and a radius around the peaks that these instances will fall within (this controls instance density, and determines the standard deviation value for the normal distribution function).


Attribute Information:

N/A


Relevant Papers:

Benedict, P.A., The Use of Synthetic Data in Dynamic Bias Selection, Proc. Of the 6th Aerospace Applications of Artificial Intelligence Conference, Dayton, Ohio, October, 1990.

Ehrenfeucht, A., Haussler, D., Kearns, M, Valiant, L. A general lower bound on the number of examples needed for learning. Proc. Computational Learning Theory, 1988, 139-154.
[Web Link]

Kononenko, I., Bratko, I., Roskar, E., Experiments in Automatic Learning of Medical Diagnostic Rules (Ljubljana, Yugoslavia: Jozef Stefan Institute, 1984).
[Web Link]

Michalski, R.S., Mozetic, I., Hong, J., Lavrac, N., The Multipurpose Incremental Learning System AQ15 and Its Testing Application to Three Medical Domains, Proc. Of the Fifth National Conference on Artificial Intelligence, Pp. 1041-1045, Morgan Kaufman, Los Altos, Ca, 1986.
[Web Link]

Mitchell, T. M. The need for biases in learning generalizations. Technical Report CBM-TR-117, May 1980.
[Web Link]

Rendell, L.A., A New Basis for State Space Learning Systems and a Successful Implementation, Artificial Intelligence 20(1983):369-392.
[Web Link]

Rendell, L. A., Cho, H. H. The effect of data character on empirical concept learning in Proc. Fifth International Conference on Artificial Intelligence Applications, March, 1989.
[Web Link]

Rendell, L. A., Benedict, P. A., Cho, H. H., Seshu, Improving the design of rule-learning systems, Proceedings of the Seventh International Conference on Expert Systems and their Applications, June, 1988.

Rendell, L., Seshu, R., Learning hard concepts through constructive induction: framework and rationale, Computational Intelligence, 1990.
[Web Link]

Rendell, L. A., Seshu, R. M., Tcheng, D. K. Layered concept learning and dynamically-variable bias management. Proceedings of the Tenth International Joint Conference on Artificial Intelligence, 1987.
[Web Link]

Russell, S., Grosof, B. Declarative bias: An overview, in P. Benjamin (Ed.), Change of Representation and Inductive Bias. Kluwer Academic Press, 1990.
[Web Link]

Utgoff, P. E. Shift of bias for inductive concept learning. Machine Learning: An Artificial Intelligence Approach, 1986, III.
[Web Link]

Utgoff, P. E., Mitchell, T. M., Acquisition of appropriate bias for inductive concept learning, Proc. National Conference on Artificial Intelligence, 1982.
[Web Link]



Citation Request:

Please refer to the Machine Learning Repository's citation policy


Supported By:

 In Collaboration With:

About  ||  Citation Policy  ||  Donation Policy  ||  Contact  ||  CML