Soft Randomized Machine Learning


Citar

Texto integral

Acesso aberto Acesso aberto
Acesso é fechado Acesso está concedido
Acesso é fechado Somente assinantes

Resumo

A new method for entropy-randomized machine learning is proposed based on empirical risk minimization instead of the exact fulfillment of empirical balance conditions. The corresponding machine learning algorithm is shown to generate a family of exponential distributions, and their structure is found.

Sobre autores

Yu. Popkov

Institute for Systems Analysis, Federal Research Center “Computer Science and Control,”; Haifa University; Yugorsk Research Institute of Information Technologies

Autor responsável pela correspondência
Email: popkov@isa.ru
Rússia, Moscow, 117312; Karmiel; Khanty-Mansiysk, Tyumen oblast

Arquivos suplementares

Arquivos suplementares
Ação
1. JATS XML

Declaração de direitos autorais © Pleiades Publishing, Ltd., 2018