Comparative Evaluation of Convergence's Speed of Learning Algorithms for Linear Classifiers by Statistical Experiments Method

• Published in: Кибернетика и вычислительная техника
• Date: 2018
• ISSN: 0454-9910
• Main Authors: Fainzilberg, L.S., Matushevych, N.A.
• Format: Article
• Language: English
• Published: Міжнародний науково-навчальний центр інформаційних технологій і систем НАН України та МОН України 2018
• Subjects: Информатика и информационные технологии
• Online Access: https://nasplib.isofts.kiev.ua/handle/123456789/142089
• Journal Title: Digital Library of Periodicals of National Academy of Sciences of Ukraine
• Cite this: Comparative Evaluation of Convergence's Speed of Learning Algorithms for Linear Classifiers by Statistical Experiments Method / L.S. Fainzilberg, N.A. Matushevych // Кибернетика и .вычислительная техника. — 2018. — № 2 (192). — С. 5-22. — Бібліогр.: 20 назв. — англ.

The purpose of the article is to investigate the properties of the Rosenblatt and Kozinets learning algorithms on the basis of statistical experiment by the Monte Carlo method. Methods. Two algorithms for linear classifiers learning have been studied: Rosenblatt and Kozinets. A number of researches...