Minimization of Empirical Risk as a Means of Choosing the Number of Hypotheses in Algebraic Machine Learning.
| Autor: | Vinogradov, D. V. |
|---|---|
| Zdroj: | Pattern Recognition & Image Analysis; Sep2023, Vol. 33 Issue 3, p525-528, 4p |
| Abstrakt: | The paper examines a new approach to assessing the number of required hypotheses about the causes of a target property. It follows the classical method of V.N. Vapnik and A.Y. Chervonenkis—minimization of the number of classification errors on the training sample. However, there is a very close analogy with the procedure of an abductive explanation of the training sample by V.K. Finn. [ABSTRACT FROM AUTHOR] |
| Databáze: | Complementary Index |
| Externí odkaz: |
|
Full text from SpringerLink