This lecture overviews Parameter estimation that has many applications in Statistics and Pattern Recognition. It covers the following topics in detail: Data analysis needs: Probabilistic data modeling, Estimation of pdf parameters (Location and dispersion parameters). Maximum Likelihood Parameter Estimation (ML Estimation for Gaussian Distributions, ML Estimation for Laplacian Distributions, Robustness of arithmetic mean and median).Maximum… Continue reading Parameter Estimation
Archives: Resources
Resource description
Hypothesis Testing
This lecture overviews Hypothesis Testing that has many applications in statistics and pattern recognition. It covers the following topics in detail: Elementary Principles, NSHT & BHT, Tests: Tests comparing mean values (T-test, Z-test), Tests detecting normal distribution (Chi-Squared test, Mardia’s test), Tests determining distribution type (Anderson-Darling Test, Kolmogorov-Smirnov Test).
Kernel methods
This lecture overviews Kernel Methods that have many applications in classification and clustering. It covers the following topics in detail: Kernel Trick. Kernel Matrix. Kernel PCA. Kernel correlation and its use in object tracking. Kernel k-means.
Dimensionality Reduction
This lecture overviews Dimensionality Reduction that has many applications in object clusring and object recognition. It covers the following topics in detail: Feature selection. Principal Component Analysis. Linear Discriminant Analysis. SVD Data Compression. Multidimensional Scaling. Non-negative matrix factorization, Learning Vector Quantization.
Graph-Based Pattern Recognition
This lecture overviews Graph-Based Pattern Recognition that has many applications in data clustering and dimensionality reduction. It covers the following topics in detail: Graph-based Clustering, Locality Preserving Projections, Locally Linear Embedding, ISOMAP, Laplacian Embedding, Linear Discriminant Analysis, Marginal Fisher Analysis, Local Fisher Discriminant Analysis, Semi-supervised Discriminant Analysis, Laplacian Support Vector Machines.
Decision Surfaces. Support Vector Machines
This lecture overviews Decision Surfaces and, in particular, Support Vector Machines that have many applications in Machine Learning and Pattern Recognition. It covers the following topics in detail: Decision surfaces. Hyperplanes. Non-linear Decision Surfaces. Quadratic (2nd degree polynomial) surfaces, Hyperellipsoid/Hyperparaboloid. Support Vector Machines, Margin Maximization, Lagrangian Primal/Dual Problem, Kernel SVM.