Statistical pattern recognition /

• Κύριος συγγραφέας: Webb, A. R. (Andrew R.)
• Μορφή: Ηλ. βιβλίο
• Γλώσσα: English
• Έκδοση: West Sussex, England ; New Jersey : Wiley, �2002.
• Έκδοση: 2nd ed.
• Θέματα: Pattern perception > Statistical methods.; Perception des structures > M�ethodes statistiques.; COMPUTERS > Optical Data Processing.; Discriminantanalyse.; Clusteranalyse.; Classificatie.; Reconhecimento de padr�oes.; Computa�c�ao gr�afica.; Computational and graphical statistics.; Electronic books.

Statistical pattern recognition is a very active area of study and research, which has seen many advances in recent years. New and emerging applications - such as data mining, web searching, multimedia data retrieval, face recognition, and cursive handwriting recognition - require robust and efficie...

Πίνακας περιεχομένων:

• 1. Introduction to statistical pattern recognition
• Statistical pattern recognition
• Stages in a pattern recognition problem
• Issues
• Supervised versus unsupervised
• Approaches to statistical pattern recognition
• Multiple regression
• Outline of book
• 2. Density estimation
• parametric
• Normal-based models
• Normal mixture models
• Bayesian estimates
• 3. Density estimation
• nonparametric
• Histogram method
• k-nearest-neighbour method
• Expansion by basis functions
• Kernel methods
• 4. Linear discriminant analysis
• Two-class algorithms
• Multiclass algorithms
• Logistic discrimination
• 5. Nonlinear discriminant analysis
• kernel methods
• Optimisation criteria
• Radial basis functions
• Nonlinear support vector machines
• 6. Nonlinear discriminant analysis
• projection methods
• The multilayer perceptron
• Projection pursuit
• 7. Tree-based methods
• Classification trees
• Multivariate adaptive regression splines
• 8. Performance
• Performance assessment
• Comparing classifier performance
• Combining classifiers
• 9. Feature selection and extraction
• Feature selection
• Linear feature extraction
• Multidimensional scaling
• 10. Clustering
• Hierarchical methods
• Quick partitions
• Mixture models
• Sum-of-squares methods
• Cluster validity
• 11. Additional topics
• Model selection
• Learning with unreliable classification
• Missing data
• Outlier detection and robust procedures
• Mixed continuous and discrete variables
• Structural risk minimisation and the Vapnik-Chervonenkis dimension
• A. Measures of dissimilarity
• B. Parameter estimation
• C. Linear algebra
• D. Data
• E. Probability theory.