Computational network theory : theoretical foundations and applications / / Edited by Matthias Dehmer, Frank Emmert-Streib, and Stefan Pickl

• Record Nr.: UNINA9910788289203321
• Pubbl/distr/stampa: Weinheim, Germany : , : Wiley-VCH Verlang GmbH & Co. KGaA, , 2015; ©2015
• ISBN: 3-527-69154-5; 3-527-69151-0
• Descrizione fisica: 1 online resource (281 p.)
• Collana: Quantitative and network biology ; ; Volume 5
• Disciplina: 006.3
• Soggetti: Electronic commerce; Computational intelligence
• Lingua di pubblicazione: Inglese
• Formato: Materiale a stampa
• Livello bibliografico: Monografia
• Note generali: Description based upon print version of record.
• Nota di bibliografia: Includes bibliographical references at the end of each chapters and index.
• Nota di contenuto: Cover; Title Page; Copyright; Dedication; Contents; Color Plates; Preface; List of Contributors; Chapter 1 Model Selection for Neural Network Models: A Statistical Perspective; 1.1 Introduction; 1.2 Feedforward Neural Network Models; 1.3 Model Selection; 1.3.1 Feature Selection by Relevance Measures; 1.3.2 Some Numerical Examples; 1.3.3 Application to Real Data; 1.4 The Selection of the Hidden Layer Size; 1.4.1 A Reality Check Approach; 1.4.2 Numerical Examples by Using the Reality Check; 1.4.3 Testing Superior Predictive Ability for Neural Network Modeling; 1.4.4 Some Numerical Results Using Test of Superior Predictive Ability1.4.5 An Application to Real Data; 1.5 Concluding Remarks; References; Chapter 2 Measuring Structural Correlations in Graphs; 2.1 Introduction; 2.1.1 Solutions for Measuring Structural Correlations; 2.2 Related Work; 2.3 Self Structural Correlation; 2.3.1 Problem Formulation; 2.3.2 The Measure; 2.3.2.1 Random Walk and Hitting Time; 2.3.2.2 Decayed Hitting Time; 2.3.3 Computing Decayed Hitting Time; 2.3.3.1 Iterative Approximation; 2.3.3.2 A Sampling Algorithm for h(vi,B); 2.3.3.3 Complexity; 2.3.4 Assessing SSC; 2.3.4.1 Estimating ρ (Vq)2.3.4.2 Estimating the Significance of ρ (Vq); ; 2.3.5 Empirical Studies; 2.3.5.1 Datasets; 2.3.5.2 Performance of DHT Approximation; 2.3.5.3 Effectiveness on Synthetic Events; 2.3.5.4 SSC of Real Event; 2.3.5.5 Scalability of Sampling-alg; 2.3.6 Discussions; 2.4 Two-Event Structural Correlation; 2.4.1 Preliminaries and Problem Formulation; 2.4.2 Measuring TESC; 2.4.2.1 The Test; 2.4.2.2 Reference Nodes; 2.4.3 Reference Node Sampling; 2.4.3.1 Batch_BFS; 2.4.3.2 Importance Sampling; 2.4.3.3 Global Sampling in Whole Graph; 2.4.3.4 Complexity Analysis; 2.4.4 Experiments; 2.4.4.1 Graph Datasets2.4.4.2 Event Simulation Methodology; 2.4.4.3 Performance Comparison; 2.4.4.4 Batch Importance Sampling; 2.4.4.5 Impact of Graph Density; 2.4.4.6 Efficiency and Scalability; 2.4.4.7 Real Events; 2.4.5 Discussions; 2.5 Conclusions; Acknowledgments; References; Chapter 3 Spectral Graph Theory and Structural Analysis of Complex Networks: An Introduction; 3.1 Introduction; 3.2 Graph Theory: Some Basic Concepts; 3.2.1 Connectivity in Graphs; 3.2.2 Subgraphs and Special Graphs; 3.3 Matrix Theory: Some Basic Concepts; 3.3.1 Trace and Determinant of a Matrix; 3.3.2 Eigenvalues and Eigenvectors of a Matrix3.4 Graph Matrices; 3.4.1 Adjacency Matrix; 3.4.2 Incidence Matrix; 3.4.3 Degree Matrix and Diffusion Matrix; 3.4.4 Laplace Matrix; 3.4.5 Cut-Set Matrix; 3.4.6 Path Matrix; 3.5 Spectral Graph Theory: Some Basic Results; 3.5.1 Spectral Characterization of Graph Connectivity; 3.5.1.1 Spectral Theory and Walks; 3.5.2 Spectral Characteristics of some Special Graphs and Subgraphs; 3.5.2.1 Tree; 3.5.2.2 Bipartite Graph; 3.5.2.3 Complete Graph; 3.5.2.4 Regular Graph; 3.5.2.5 Line Graph; 3.5.3 Spectral Theory and Graph Colouring; 3.5.4 Spectral Theory and Graph Drawing
• Sommario/riassunto: This comprehensive introduction to computational network theory as a branch of network theory builds on the understanding that such networks are a tool to derive or verify hypotheses by applying computational techniques to large scale network data.The highly experienced team of editors and high-profile authors from around the world present and explain a number of methods that are representative of computational network theory, derived from graph theory, as well as computational and statistical techniques. With its coherent structure and homogenous style, this reference is equally suitable for