Machine learning paradigms

• Verfasst von: Lampropoulos, Aristomenis S. [VerfasserIn]
• Verfasst von: Tsichrintzēs, Geōrgios [VerfasserIn]
• Titel: Machine learning paradigms
• Titelzusatz: applications in recommender systems
• Verf.angabe: Aristomenis S. Lampropoulos, George A. Tsihrintzis
• Verlagsort: Cham ; Heidelberg
• Verlag: Springer
• E-Jahr: 2015
• Jahr: [2015]
• Umfang: 1 Online-Ressource (xv, 125 Seiten)
• Illustrationen: Illustrationen
• Gesamttitel/Reihe: Intelligent systems reference library ; volume 92
• Fussnoten: Description based upon print version of record
• ISBN: 978-3-319-19135-5
• Schlagwörter: (s)Anwendungsprogramm / (s)Empfehlungssystem / (s)Multimedia
• Schlagwörter: (s)Maschinelles Lernen
• Datenträger: Online-Ressource
• Sprache: eng
• Bibliogr. Hinweis: Erscheint auch als : Druck-Ausgabe: Machine learning paradigms. - Cham [u.a.] : Springer, 2015. - XV, 125 S.
• Sach-SW: Artificial intelligence
• Sach-SW: Computer vision
• Sach-SW: Engineering
• Sach-SW: Electronic books
• K10plus-PPN: 832479497
• K10plus-PPN:
  Universitätsbibliothek
• Lokale URL UB: Zum Volltext

Abstract

This timely book presents Applications in Recommender Systems which are making recommendations using machine learning algorithms trained via examples of content the user likes or dislikes. Recommender systems built on the assumption of availability of both positive and negative examples do not perform well when negative examples are rare. It is exactly this problem that the authors address in the monograph at hand. Specifically, the books approach is based on one-class classification methodologies that have been appearing in recent machine learning research. The blending of recommender system

Abstract

Foreword; Preface; Acknowledgments; Contents; 1 Introduction; 1.1 Introduction to Recommender Systems; 1.2 Formulation of the Recommendation Problem; 1.2.1 The Input to a Recommender System; 1.2.2 The Output of a Recommender System; 1.3 Methods of Collecting Knowledge About User Preferences; 1.3.1 The Implicit Approach; 1.3.2 The Explicit Approach; 1.3.3 The Mixing Approach; 1.4 Motivation of the Book; 1.5 Contribution of the Book; 1.6 Outline of the Book; References; 2 Review of Previous Work Related to Recommender Systems; 2.1 Content-Based Methods; 2.2 Collaborative Methods

Abstract

2.2.1 User-Based Collaborative Filtering Systems2.2.2 Item-Based Collaborative Filtering Systems; 2.2.3 Personality Diagnosis; 2.3 Hybrid Methods; 2.3.1 Adding Content-Based Characteristics to Collaborative Models; 2.3.2 Adding Collaborative Characteristics to Content-Based Models; 2.3.3 A Single Unifying Recommendation Model; 2.3.4 Other Types of Recommender Systems; 2.4 Fundamental Problems of Recommender Systems; References; 3 The Learning Problem; 3.1 Introduction; 3.2 Types of Learning; 3.3 Statistical Learning; 3.3.1 Classical Parametric Paradigm

Abstract

3.3.2 General Nonparametric---Predictive Paradigm3.3.3 Transductive Inference Paradigm; 3.4 Formulation of the Learning Problem; 3.5 The Problem of Classification; 3.5.1 Empirical Risk Minimization; 3.5.2 Structural Risk Minimization; 3.6 Support Vector Machines; 3.6.1 Basics of Support Vector Machines; 3.6.2 Multi-class Classification Based on SVM; 3.7 One-Class Classification; 3.7.1 One-Class SVM Classification; 3.7.2 Recommendation as a One-Class Classification Problem; References; 4 Content Description of Multimedia Data; 4.1 Introduction; 4.2 MPEG-7; 4.2.1 Visual Content Descriptors

Abstract

4.2.2 Audio Content Descriptors4.3 MARSYAS: Audio Content Features; 4.3.1 Music Surface Features; 4.3.2 Rhythm Features and Tempo; 4.3.3 Pitch Features; References; 5 Similarity Measures for Recommendations Based on Objective Feature Subset Selection; 5.1 Introduction; 5.2 Objective Feature-Based Similarity Measures; 5.3 Architecture of MUSIPER; 5.4 Incremental Learning; 5.5 Realization of MUSIPER; 5.5.1 Computational Realization of Incremental Learning; 5.6 MUSIPER Operation Demonstration; 5.7 MUSIPER Evaluation Process; 5.8 System Evaluation Results; References

Abstract

6 Cascade Recommendation Methods6.1 Introduction; 6.2 Cascade Content-Based Recommendation; 6.3 Cascade Hybrid Recommendation; 6.4 Measuring the Efficiency of the Cascade Classification Scheme; References; 7 Evaluation of Cascade Recommendation Methods; 7.1 Introduction; 7.2 Comparative Study of Recommendation Methods; 7.3 One-Class SVM---Fraction: Analysis; 8 Conclusions and Future Work; 8.1 Summary and Conclusions; 8.2 Current and Future Work