论文信息 - An Idea for Universal Generator of Hypotheses

An Idea for Universal Generator of Hypotheses

We know that the task of Machine Learning (ML) is defined as finding of rules for the class on the basis of learning examples for classification of unknown object(s). But we can use rules also for describing the class data– who/what are they? which is the task of Data Analysis and Data Mining. There are several methods for solving this task, for example, Determination Analysis (DA) and Generator of Hypotheses (GH). In the paper we describe an idea for Universal Generator of Hypotheses, the complex method which can solve the tasks of DA and GH and several new ones.

Rein Kuusik | Grete Lind

[1] Rein Kuusik,et al. Machine Learning Task as a Diclique Extracting Task , 2009, 2009 Sixth International Conference on Fuzzy Systems and Knowledge Discovery.

[2] J. Ross Quinlan,et al. Induction of Decision Trees , 1986, Machine Learning.

[3] Rein Kuusik,et al. GENERATOR OF HYPOTHESES - AN APPROACH OF DATA MINING BASED ON MONOTONE SYSTEMS THEORY , 2007 .

[4] Matjaz Gams,et al. Review of Five Empirical Learning Systems Within a Proposed Schemata , 1987, EWSL.

[5] R. Kuusik,et al. New developments for determinacy analysis: diclique-based approach , 2008 .

[6] Peter Clark,et al. Induction in Noisy Domains , 1987, EWSL.

[7] Rein Kuusik,et al. New Developments of Determinacy Analysis , 2011, ADMA.

[8] Monotone Systems approach in Inductive Learning , .

[9] Wei-Yin Loh,et al. Classification and regression trees , 2011, WIREs Data Mining Knowl. Discov..

[10] Rein Kuusik,et al. Some Developments of Determinacy Analysis , 2010, ADMA.

[11] J. Ross Quinlan,et al. Learning Efficient Classification Procedures and Their Application to Chess End Games , 1983 .