Minimization of Empirical Risk as a Means of Choosing the Number of Hypotheses in Algebraic Machine Learning

被引：0

作者：

Vinogradov, D. V. ^{[1
]}

机构：

[1] Russian Acad Sci, Fed Res Ctr Comp Sci & Control, Moscow 119333, Russia

来源：

PATTERN RECOGNITION AND IMAGE ANALYSIS | 2023年 / 33卷 / 03期

关键词：

Markov chain; inductive generalization; empirical risk; prediction by analogy; abductive explanation; SIMILARITY;

D O I：

10.1134/S1054661823030458

中图分类号：

TP39 [计算机的应用];

学科分类号：

081203 ; 0835 ;

摘要：

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.

引用

页码：525 / 528

页数：4

共 50 条

[41] The Q-norm complexity measure and the minimum gradient method:: A novel approach to the machine learning structural risk minimization problem
Vieira, D. A. G.
Takahashi, Ricardo H. C.
Palade, Vasile
Vasconcelos, J. A.
Caminhas, W. M.
IEEE TRANSACTIONS ON NEURAL NETWORKS, 2008, 19 (08): : 1415 - 1430
[42] Machine Learning-Based Risk-Aware Congestion Control Scheme for Minimization of Information Loss in Dense VANET Environment
Dhakad, Bhupendra
Shrivastava, Laxmi
JOURNAL OF CIRCUITS SYSTEMS AND COMPUTERS, 2024, 33 (09)
[43] Inexact stochastic subgradient projection method for stochastic equilibrium problems with nonmonotone bifunctions: application to expected risk minimization in machine learning
Iiduka, Hideaki
JOURNAL OF GLOBAL OPTIMIZATION, 2021, 80 (02) : 479 - 505
[44] Application of machine learning methods in risk assessment of fracture associated with antihypertensives in older people with a large number of confounders
Guo, Yuchen
Khalid, Sara
Prieto-Alhambra, Daniel
Strauss, Victoria
PHARMACOEPIDEMIOLOGY AND DRUG SAFETY, 2023, 32 : 500 - 500
[45] Why predicting risk can't identify 'risk factors': empirical assessment of model stability in machine learning across observational health databases
Markus, Aniek F.
Rijnbeek, Peter R.
Reps, Jenna M.
MACHINE LEARNING FOR HEALTHCARE CONFERENCE, VOL 182, 2022, 182 : 828 - 852
[46] Novel risk assessment tools for the climate-induced mechanical decay of wooden structures: Empirical and machine learning approaches
Califano, A.
Baiesi, M.
Bertolin, C.
FORCES IN MECHANICS, 2022, 7
[47] Empirical Risk-aware Machine Learning on Trojan-Horse Detection for Trusted Quantum Key Distribution Networks
Chou, Hong-Fu
Vu, Thang X.
Maity, Ilora
Garces-Socarras, Luis M.
Gonzalez-Rios, Jorge L.
Merlano-Duncan, Juan Carlos
Ma, Sean Longyu
Chatzinotas, Symeon
Ottersten, Björn
arXiv,
[48] Value-Enhancing Effect of Climate Change Risk Disclosure by Firms: Empirical Evidence Based on Textual Analysis and Machine Learning
Guo, Wenwei
Mo, Baoling
Chen, Yanling
Huang, Zicong
EMERGING MARKETS FINANCE AND TRADE, 2025, 61 (02) : 307 - 326
[49] Machine-learning-based risk assessment tool to rule out empirical use of ESBL-targeted therapy in endemic areas
Ravkin, H. D.
Ravkin, R. M.
Rubin, E.
Nesher, L.
JOURNAL OF HOSPITAL INFECTION, 2024, 149 : 90 - 97
[50] Technical risk model of machine learning based software project development - A multinational empirical study using modified Delphi-AHP method
Lin, Ching-Te
Huang, Sun-Jen
INFORMATION AND SOFTWARE TECHNOLOGY, 2024, 171

← 1 2 3 4 5 →