Statistical Learning Theory
Статистическая теория обучения
1999-11-01
SCID: 54.1/bveavnhq
Discuss with AI
function estimationgeneralization theorylearning consistencysmall-sample learningstatistical learning theory
Figures from the paper
Abstract (AI)
A comprehensive look at learning and generalization theory. The statistical theory of learning and generalization concerns the problem of choosing desired functions on the basis of empirical data. Highly applicable to a variety of computer science and robotics fields, this book offers lucid coverage of the theory as a whole. Presenting a method for determining the necessary and sufficient conditions for consistency of learning process, the author covers function estimates from small data pools, applying these estimations to real-life problems, and much more.
Key Findings
1
Claims broad applicability of the theory to computer science and robotics domains through lucid, comprehensive exposition.
2
Covers estimation of functions from small data pools and applies these estimations to real-life problems.
3
Presents a unified statistical theory of learning and generalization focused on choosing functions from empirical data.
4
Provides a method to determine necessary and sufficient conditions for consistency of learning processes.
Research Object
Statistical theory of learning and generalization (learning processes selecting functions from empirical data)
Research Subject
Conditions for consistency and generalization of learning processes, including function estimation from small data samples and applicability to real-world problems
Publication Details
Publication Date
1999-11-01
Journal
Publisher
ISSN
Cited by
26899
Access Type
Author Information
Download PDF
Subscribe to digest
Cited by17
Gradient-based learning applied to document recognition1998
Data mining: concepts and techniques2012
Gaussian Processes for Machine Learning2005
The Graph Neural Network Model2008
mixup: Beyond Empirical Risk Minimization2017
Semi-Supervised Learning2006
A theory of learning from different domains2009
Optimization Methods for Large-Scale Machine Learning2018
A survey on semi-supervised learning2019
Toward Causal Representation Learning2021
A Unifying Review of Deep and Shallow Anomaly Detection2021
Data-driven modelling: some past experiences and new approaches2007
A survey on Data Mining approaches for Healthcare2013
Machine Learning a General-Purpose Interatomic Potential for Silicon2018
Investigating the determinants of performance in machine learning for protein fitness prediction2025
Data-Driven Distributionally Robust Optimization Using the Wasserstein Metric: Performance Guarantees and Tractable Reformulations2017
Length-dependent prediction of protein intrinsic disorder2006