Design principles for inductive inference procedures

Authors:
I. V. Sergienko;A. M. Gupal
Affiliations:
V. M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, Kiev, Ukraine;V. M. Glushkov Institute of Cybernetics, National Academy of Sciences of Ukraine, Kiev, Ukraine
Venue:
Cybernetics and Systems Analysis
Year:
2006

Citing 0
Cited 2

Predicting protein secondary structure based on Bayesian classification procedures on Markovian chains

Cybernetics and Systems Analysis
Bayesian approach, theory of empirical risk minimization. Comparative analysis

Cybernetics and Systems Analysis

Quantified Score

Hi-index	0.00

Visualization

Abstract

The behavior of inductive inference procedures depending on the content of a learning sample is analyzed. It is shown that if a learning sample contains no information on some class of objects or statistical information on a priori probabilities of classes, then any procedure performs unpredictably badly and its error is strictly positive.