Linked e-resources
Details
Table of Contents
Preface; Contents; 1 From Binary NMF to Variational Bayes NMF: A Probabilistic Approach; 1.1 Motivation; 1.2 NMF for Binary Data Sets; 1.2.1 Binary NMF: A Poisson Yield Model; 1.2.2 Bernoulli Likelihood and Gradient Ascent Optimization; 1.2.3 Heuristic Multiplicative Update Rules; 1.2.4 Applications to Wafer Maps; 1.2.5 Logistic NMF; 1.2.6 Related Works for Binary Data Sets; 1.3 Probabilistic Approaches to NMF ; 1.3.1 NMF as a Constrained Optimization Problem; 1.3.2 Estimating Posterior Distributions of Latent Factors Without Prior Knowledge; 1.3.3 Algorithms for Minimum Volume NMF.
1.3.4 Bayesian Model Order Selection1.3.5 VBNMF Simulations on Toy Data Sets; 1.4 Conclusion; References; 2 Nonnegative Matrix Factorizations for Intelligent Data Analysis; 2.1 Introduction; 2.2 Intelligent Data Analysis; 2.2.1 Dimensionality Reduction Techniques; 2.3 Nonnegative Matrix Factorization; 2.3.1 NMF Mathematical Formulation; 2.3.2 Interpretation of the Basis and Encoding Matrices; 2.3.3 Comparison of NMF and PCA; 2.4 Constrained NMF; 2.4.1 Sparse NMF; 2.4.2 Orthogonal NMF and Clustering Capabilities; 2.4.3 Semi-Supervised NMF.
2.5 An Illustrative Example: NMF for Educational Data Mining2.6 Conclusions; References; 3 Automatic Extractive Multi-document Summarization Based on Archetypal Analysis; 3.1 Introduction; 3.2 Related Work; 3.3 Archetypal Analysis; 3.4 The Proposed Approach; 3.5 Experiments; 3.6 Conclusion and Further Work; References; 4 Bounded Matrix Low Rank Approximation; 4.1 Introduction; 4.2 Related Work; 4.2.1 Our Contributions; 4.3 Foundations; 4.3.1 NMF and Block Coordinate Descent; 4.3.2 Bounded Matrix Low Rank Approximation; 4.3.3 Bounding Existing ALS Algorithms (BALS); 4.4 Implementations.
4.4.1 Bounded Matrix Low Rank Approximation4.4.2 Scaling up Bounded Matrix Low Rank Approximation; 4.4.3 Bounding Existing ALS Algorithms (BALS); 4.4.4 Parameter Tuning; 4.5 Experimentation; 4.6 Conclusion; References; 5 A Modified NMF-Based Filter Bank Approach for Enhancement of Speech Data in Nonstationary Noise; 5.1 Introduction; 5.2 Proposed Speech Enhancement Method; 5.2.1 Filter Bank; 5.2.2 Modified NMF; 5.3 Experiment; 5.3.1 Data; 5.3.2 Parameters Used; 5.3.3 Results and Analysis; 5.4 Discussion and Conclusion; References.
1.3.4 Bayesian Model Order Selection1.3.5 VBNMF Simulations on Toy Data Sets; 1.4 Conclusion; References; 2 Nonnegative Matrix Factorizations for Intelligent Data Analysis; 2.1 Introduction; 2.2 Intelligent Data Analysis; 2.2.1 Dimensionality Reduction Techniques; 2.3 Nonnegative Matrix Factorization; 2.3.1 NMF Mathematical Formulation; 2.3.2 Interpretation of the Basis and Encoding Matrices; 2.3.3 Comparison of NMF and PCA; 2.4 Constrained NMF; 2.4.1 Sparse NMF; 2.4.2 Orthogonal NMF and Clustering Capabilities; 2.4.3 Semi-Supervised NMF.
2.5 An Illustrative Example: NMF for Educational Data Mining2.6 Conclusions; References; 3 Automatic Extractive Multi-document Summarization Based on Archetypal Analysis; 3.1 Introduction; 3.2 Related Work; 3.3 Archetypal Analysis; 3.4 The Proposed Approach; 3.5 Experiments; 3.6 Conclusion and Further Work; References; 4 Bounded Matrix Low Rank Approximation; 4.1 Introduction; 4.2 Related Work; 4.2.1 Our Contributions; 4.3 Foundations; 4.3.1 NMF and Block Coordinate Descent; 4.3.2 Bounded Matrix Low Rank Approximation; 4.3.3 Bounding Existing ALS Algorithms (BALS); 4.4 Implementations.
4.4.1 Bounded Matrix Low Rank Approximation4.4.2 Scaling up Bounded Matrix Low Rank Approximation; 4.4.3 Bounding Existing ALS Algorithms (BALS); 4.4.4 Parameter Tuning; 4.5 Experimentation; 4.6 Conclusion; References; 5 A Modified NMF-Based Filter Bank Approach for Enhancement of Speech Data in Nonstationary Noise; 5.1 Introduction; 5.2 Proposed Speech Enhancement Method; 5.2.1 Filter Bank; 5.2.2 Modified NMF; 5.3 Experiment; 5.3.1 Data; 5.3.2 Parameters Used; 5.3.3 Results and Analysis; 5.4 Discussion and Conclusion; References.