Note: Intro -- Title -- Preface -- Contents -- Introduction -- General Background -- Historical Background of Multi-source Learning and Data Fusion -- Canonical Correlation and Its Probabilistic Interpretation -- Inductive Logic Programming and the Multi-source Learning Search Space -- Additive Models -- Bayesian Networks for Data Fusion -- Kernel-based Data Fusion -- Topics of This Book -- Chapter by Chapter Overview -- References -- Rayleigh Quotient-Type Problems in Machine Learning -- Optimization of Rayleigh Quotient -- Rayleigh Quotient and Its Optimization -- Generalized Rayleigh Quotient -- Trace Optimization of Generalized Rayleigh Quotient-Type Problems -- Rayleigh Quotient-Type Problems in Machine Learning -- Principal Component Analysis -- Canonical Correlation Analysis -- Fisher Discriminant Analysis -- k-means Clustering -- Spectral Clustering -- Kernel-Laplacian Clustering -- One Class Support Vector Machine -- Summary -- References -- Ln-norm Multiple Kernel Learning and Least Squares Support Vector Machines -- Background -- Acronyms -- The Norms of Multiple Kernel Learning -- L-norm MKL -- L2-norm MKL -- Ln-norm MKL -- One Class SVM MKL -- Support Vector Machine MKL for Classification -- The Conic Formulation -- The Semi Infinite Programming Formulation -- Least Squares Support Vector Machines MKL for Classification -- The Conic Formulation -- The Semi Infinite Programming Formulation -- Weighted SVM MKL and Weighted LSSVM MKL -- Weighted SVM -- Weighted SVM MKL -- Weighted LSSVM -- Weighted LSSVM MKL -- Summary of Algorithms -- Numerical Experiments -- Overview of the Convexity and Complexity -- QP Formulation Is More Efficient than SOCP -- SIP Formulation Is More Efficient than QCQP -- MKL Applied to Real Applications -- Experimental Setup and Data Sets -- Results -- Discussions -- Summary -- References. , Optimized Data Fusion for Kernel k-means Clustering -- Introduction -- Objective of k-means Clustering -- Optimizing Multiple Kernels for k-means -- Bi-level Optimization of k-means on Multiple Kernels -- The Role of Cluster Assignment -- Optimizing the Kernel Coefficients as KFD -- Solving KFD as LSSVM Using Multiple Kernels -- Optimized Data Fusion for Kernel k-means Clustering (OKKC) -- Computational Complexity -- Experimental Results -- Data Sets and Experimental Settings -- Results -- Summary -- References -- Multi-view Text Mining for Disease Gene Prioritization and Clustering -- Introduction -- Background: Computational Gene Prioritization -- Background: Clustering by Heterogeneous Data Sources -- Single View Gene Prioritization: A Fragile Model with Respect to the Uncertainty -- Data Fusion for Gene Prioritization: Distribution Free Method -- Multi-view Text Mining for Gene Prioritization -- Construction of Controlled Vocabularies from Multiple Bio-ontologies -- Vocabularies Selected from Subsets of Ontologies -- Merging and Mapping of Controlled Vocabularies -- Text Mining -- Dimensionality Reduction of Gene-By-Term Data by Latent Semantic Indexing -- Algorithms and Evaluation of Gene Prioritization Task -- Benchmark Data Set of Disease Genes -- Results of Multi-view Prioritization -- Multi-view Performs Better than Single View -- Effectiveness of Multi-view Demonstrated on Various Number of Views -- Effectiveness of Multi-view Demonstrated on Disease Examples -- Multi-view Text Mining for Gene Clustering -- Algorithms and Evaluation of Gene Clustering Task -- Benchmark Data Set of Disease Genes -- Results of Multi-view Clustering -- Multi-view Performs Better than Single View -- Dimensionality Reduction of Gene-By-Term Profiles for Clustering -- Multi-view Approach Is Better than Merging Vocabularies. , Effectiveness of Multi-view Demonstrated on Various Numbers of Views -- Effectiveness of Multi-view Demonstrated on Disease Examples -- Discussions -- Summary -- References -- Optimized Data Fusion for k-means Laplacian Clustering -- Introduction -- Acronyms -- Combine Kernel and Laplacian for Clustering -- Combine Kernel and Laplacian as Generalized Rayleigh Quotient for Clustering -- Combine Kernel and Laplacian as Additive Models for Clustering -- Clustering by Multiple Kernels and Laplacians -- Optimize A with Given -- Optimize with Given A -- Algorithm: Optimized Kernel Laplacian Clustering -- Data Sets and Experimental Setup -- Results -- Summary -- References -- Weighted Multiple Kernel Canonical Correlation -- Introduction -- Acronyms -- Weighted Multiple Kernel Canonical Correlation -- Linear CCA on Multiple Data Sets -- Multiple Kernel CCA -- Weighted Multiple Kernel CCA -- Computational Issue -- Standard Eigenvalue Problem for WMKCCA -- Incomplete Cholesky Decomposition -- Incremental Eigenvalue Solution for WMKCCA -- Learning from Heterogeneous Data Sources by WMKCCA -- Experiment -- Classification in the Canonical Spaces -- Efficiency of the Incremental EVD Solution -- Visualization of Data in the Canonical Spaces -- Summary -- References -- Cross-Species Candidate Gene Prioritizationwith MerKator -- Introduction -- Data Sources -- Kernel Workflow -- Approximation of Kernel Matrices Using Incomplete Cholesky Decomposition -- Kernel Centering -- Missing Values -- Cross-Species Integration of Prioritization Scores -- Software Structure and Interface -- Results and Discussion -- Summary -- References -- Conclusion -- Index.