Email this article Soft Randomized Machine Learning
- Authors: Popkov Y.S.1,2,3
-
Affiliations:
- Institute for Systems Analysis, Federal Research Center “Computer Science and Control,”
- Haifa University
- Yugorsk Research Institute of Information Technologies
- Issue: Vol 98, No 3 (2018)
- Pages: 646-647
- Section: Mathematics
- URL: https://journals.rcsi.science/1064-5624/article/view/225604
- DOI: https://doi.org/10.1134/S1064562418070293
- ID: 225604
Cite item
Open Access
Access granted
Subscription Access
Abstract
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.
About the authors
Yu. S. Popkov
Institute for Systems Analysis, Federal Research Center “Computer Science and Control,”; Haifa University; Yugorsk Research Institute of Information Technologies
Author for correspondence.
Email: popkov@isa.ru
Russian Federation, Moscow, 117312; Karmiel; Khanty-Mansiysk, Tyumen oblast
Supplementary files
