Abstract and Applied Analysis

Learning Theory


Publishing date
28 Feb 2014
Status
Published
Submission deadline
11 Oct 2013

Lead Editor
Guest Editors

1Department of Mathematics, City University of Hong Kong, Hong Kong

2Department of Mathematical Sciences, Middle Tennessee State University, Murfreesboro, TN, USA

3College of Engineering, Mathematics and Physical Sciences, University of Exeter, Exeter, UK


Learning Theory

Description

Machine learning is extensively used in commercial systems and industrial companies ranging from computer vision and bioinformatics to social web mining. As the field has evolved, there has been an increased emphasis on understanding its mathematical underpinnings. There is no doubt that machine learning has rapidly progressed from a discipline studied primarily by researchers in artificial intelligence to a much broader discipline also studied by applied mathematicians and statisticians.

The main focus of this special issue will be on theoretical aspects of machine learning algorithms. The special issue will serve as an international forum for researches into machine learning and applied mathematics and statistics to summarize the most recent developments and ideas in the fast developing field, with a special emphasis given to learning theory. Both original research articles and review articles are welcome. Potential topics include, but are not limited to:

  • Generalization and consistency of learning algorithms
  • Approximation theory related to learning theory
  • Characterization of reproducing kernel Hilbert space (RKHS)
  • Concentration inequality and empirical process theory for analyzing learning algorithms
  • Other theoretical analysis of novel machine learning methods

Before submission authors should carefully read over the journal's Author Guidelines, which are located at http://www.hindawi.com/journals/aaa/guidelines/. Prospective authors should submit an electronic copy of their complete manuscript through the journal Manuscript Tracking System at http://mts.hindawi.com/author/submit/journals/aaa/lnt/ according to the following timetable:


Articles

  • Special Issue
  • - Volume 2014
  • - Article ID 138960
  • - Editorial

Learning Theory

Ding-Xuan Zhou | Qiang Wu | Yiming Ying
  • Special Issue
  • - Volume 2014
  • - Article ID 781068
  • - Research Article

Strong Inequalities for Hermite-Fejér Interpolations and Characterization of -Functionals

Gongqiang You
  • Special Issue
  • - Volume 2013
  • - Article ID 694181
  • - Research Article

The Learning Rates of Regularized Regression Based on Reproducing Kernel Banach Spaces

Baohuai Sheng | Peixin Ye
  • Special Issue
  • - Volume 2013
  • - Article ID 715275
  • - Research Article

Least Square Regularized Regression for Multitask Learning

Yong-Li Xu | Di-Rong Chen | Han-Xiong Li
  • Special Issue
  • - Volume 2013
  • - Article ID 260573
  • - Research Article

Wavelet Optimal Estimations for Density Functions under Severely Ill-Posed Noises

Rui Li | Youming Liu
  • Special Issue
  • - Volume 2013
  • - Article ID 927827
  • - Research Article

Regularized Ranking with Convex Losses and -Penalty

Heng Chen | Jitao Wu
  • Special Issue
  • - Volume 2013
  • - Article ID 715683
  • - Research Article

Density Problem and Approximation Error in Learning Theory

Ding-Xuan Zhou
  • Special Issue
  • - Volume 2013
  • - Article ID 540725
  • - Research Article

Kernel Sliced Inverse Regression: Regularization and Consistency

Qiang Wu | Feng Liang | Sayan Mukherjee
  • Special Issue
  • - Volume 2013
  • - Article ID 154637
  • - Research Article

Uniform Bounds of Aliasing and Truncated Errors in Sampling Series of Functions from Anisotropic Besov Class

Peixin Ye | Yongjie Han
  • Special Issue
  • - Volume 2013
  • - Article ID 174802
  • - Research Article

Stability Analysis of Learning Algorithms for Ontology Similarity Computation

Wei Gao | Tianwei Xu
Abstract and Applied Analysis
 Journal metrics
Acceptance rate14%
Submission to final decision40 days
Acceptance to publication54 days
CiteScore1.300
Impact Factor-
 Submit

We are committed to sharing findings related to COVID-19 as quickly as possible. We will be providing unlimited waivers of publication charges for accepted research articles as well as case reports and case series related to COVID-19. Review articles are excluded from this waiver policy. Sign up here as a reviewer to help fast-track new submissions.