{ "doc_name": "PRML.pdf", "structure": [ { "title": "Preface", "start_index": 1, "end_index": 6, "node_id": "0000" }, { "title": "Preface", "start_index": 7, "end_index": 10, "node_id": "0001" }, { "title": "Mathematical notation", "start_index": 11, "end_index": 13, "node_id": "0002" }, { "title": "Contents", "start_index": 13, "end_index": 20, "node_id": "0003" }, { "title": "Introduction", "start_index": 21, "end_index": 24, "nodes": [ { "title": "Example: Polynomial Curve Fitting", "start_index": 24, "end_index": 32, "node_id": "0005" }, { "title": "Probability Theory", "start_index": 32, "end_index": 37, "nodes": [ { "title": "Probability densities", "start_index": 37, "end_index": 39, "node_id": "0007" }, { "title": "Expectations and covariances", "start_index": 39, "end_index": 41, "node_id": "0008" }, { "title": "Bayesian probabilities", "start_index": 41, "end_index": 44, "node_id": "0009" }, { "title": "The Gaussian distribution", "start_index": 44, "end_index": 48, "node_id": "0010" }, { "title": "Curve fitting re-visited", "start_index": 48, "end_index": 50, "node_id": "0011" }, { "title": "Bayesian curve fitting", "start_index": 50, "end_index": 52, "node_id": "0012" } ], "node_id": "0006" }, { "title": "Model Selection", "start_index": 52, "end_index": 53, "node_id": "0013" }, { "title": "The Curse of Dimensionality", "start_index": 53, "end_index": 58, "node_id": "0014" }, { "title": "Decision Theory", "start_index": 58, "end_index": 59, "nodes": [ { "title": "Minimizing the misclassification rate", "start_index": 59, "end_index": 61, "node_id": "0016" }, { "title": "Minimizing the expected loss", "start_index": 61, "end_index": 62, "node_id": "0017" }, { "title": "The reject option", "start_index": 62, "end_index": 62, "node_id": "0018" }, { "title": "Inference and decision", "start_index": 62, "end_index": 66, "node_id": "0019" }, { "title": "Loss functions for regression", "start_index": 66, "end_index": 68, "node_id": "0020" } ], "node_id": "0015" }, { "title": "Information Theory", "start_index": 68, "end_index": 75, "nodes": [ { "title": "Relative entropy and mutual information", "start_index": 75, "end_index": 78, "node_id": "0022" } ], "node_id": "0021" } ], "node_id": "0004" }, { "title": "Exercises", "start_index": 78, "end_index": 87, "node_id": "0023" }, { "title": "Probability Distributions", "start_index": 87, "end_index": 88, "nodes": [ { "title": "Binary Variables", "start_index": 88, "end_index": 91, "nodes": [ { "title": "The beta distribution", "start_index": 91, "end_index": 94, "node_id": "0026" } ], "node_id": "0025" }, { "title": "Multinomial Variables", "start_index": 94, "end_index": 96, "nodes": [ { "title": "The Dirichlet distribution", "start_index": 96, "end_index": 98, "node_id": "0028" } ], "node_id": "0027" }, { "title": "The Gaussian Distribution", "start_index": 98, "end_index": 105, "nodes": [ { "title": "Conditional Gaussian distributions", "start_index": 105, "end_index": 108, "node_id": "0030" }, { "title": "Marginal Gaussian distributions", "start_index": 108, "end_index": 110, "node_id": "0031" }, { "title": "Bayes\u2019 theorem for Gaussian variables", "start_index": 110, "end_index": 113, "node_id": "0032" }, { "title": "Maximum likelihood for the Gaussian", "start_index": 113, "end_index": 114, "node_id": "0033" }, { "title": "Sequential estimation", "start_index": 114, "end_index": 117, "node_id": "0034" }, { "title": "Bayesian inference for the Gaussian", "start_index": 117, "end_index": 122, "node_id": "0035" }, { "title": "Student\u2019s t-distribution", "start_index": 122, "end_index": 125, "node_id": "0036" }, { "title": "Periodic variables", "start_index": 125, "end_index": 130, "node_id": "0037" }, { "title": "Mixtures of Gaussians", "start_index": 130, "end_index": 133, "node_id": "0038" } ], "node_id": "0029" }, { "title": "The Exponential Family", "start_index": 133, "end_index": 136, "nodes": [ { "title": "Maximum likelihood and sufficient statistics", "start_index": 136, "end_index": 137, "node_id": "0040" }, { "title": "Conjugate priors", "start_index": 137, "end_index": 137, "node_id": "0041" }, { "title": "Noninformative priors", "start_index": 137, "end_index": 140, "node_id": "0042" } ], "node_id": "0039" }, { "title": "Nonparametric Methods", "start_index": 140, "end_index": 142, "nodes": [ { "title": "Kernel density estimators", "start_index": 142, "end_index": 144, "node_id": "0044" }, { "title": "Nearest-neighbour methods", "start_index": 144, "end_index": 147, "node_id": "0045" } ], "node_id": "0043" } ], "node_id": "0024" }, { "title": "Exercises", "start_index": 147, "end_index": 156, "node_id": "0046" }, { "title": "Linear Models for Regression", "start_index": 157, "end_index": 158, "nodes": [ { "title": "Linear Basis Function Models", "start_index": 158, "end_index": 160, "nodes": [ { "title": "Maximum likelihood and least squares", "start_index": 160, "end_index": 163, "node_id": "0049" }, { "title": "Geometry of least squares", "start_index": 163, "end_index": 163, "node_id": "0050" }, { "title": "Sequential learning", "start_index": 163, "end_index": 164, "node_id": "0051" }, { "title": "Regularized least squares", "start_index": 164, "end_index": 166, "node_id": "0052" }, { "title": "Multiple outputs", "start_index": 166, "end_index": 167, "node_id": "0053" } ], "node_id": "0048" }, { "title": "The Bias-Variance Decomposition", "start_index": 167, "end_index": 172, "node_id": "0054" }, { "title": "Bayesian Linear Regression", "start_index": 172, "end_index": 172, "nodes": [ { "title": "Parameter distribution", "start_index": 172, "end_index": 176, "node_id": "0056" }, { "title": "Predictive distribution", "start_index": 176, "end_index": 179, "node_id": "0057" }, { "title": "Equivalent kernel", "start_index": 179, "end_index": 181, "node_id": "0058" } ], "node_id": "0055" }, { "title": "Bayesian Model Comparison", "start_index": 181, "end_index": 185, "node_id": "0059" }, { "title": "The Evidence Approximation", "start_index": 185, "end_index": 186, "nodes": [ { "title": "Evaluation of the evidence function", "start_index": 186, "end_index": 188, "node_id": "0061" }, { "title": "Maximizing the evidence function", "start_index": 188, "end_index": 190, "node_id": "0062" }, { "title": "Effective number of parameters", "start_index": 190, "end_index": 192, "node_id": "0063" } ], "node_id": "0060" }, { "title": "Limitations of Fixed Basis Functions", "start_index": 192, "end_index": 193, "node_id": "0064" } ], "node_id": "0047" }, { "title": "Exercises", "start_index": 193, "end_index": 199, "node_id": "0065" }, { "title": "Linear Models for Classification", "start_index": 199, "end_index": 201, "nodes": [ { "title": "Discriminant Functions", "start_index": 201, "end_index": 201, "nodes": [ { "title": "Two classes", "start_index": 201, "end_index": 202, "node_id": "0068" }, { "title": "Multiple classes", "start_index": 202, "end_index": 204, "node_id": "0069" }, { "title": "Least squares for classification", "start_index": 204, "end_index": 206, "node_id": "0070" }, { "title": "Fisher\u2019s linear discriminant", "start_index": 206, "end_index": 209, "node_id": "0071" }, { "title": "Relation to least squares", "start_index": 209, "end_index": 211, "node_id": "0072" }, { "title": "Fisher\u2019s discriminant for multiple classes", "start_index": 211, "end_index": 212, "node_id": "0073" }, { "title": "The perceptron algorithm", "start_index": 212, "end_index": 216, "node_id": "0074" } ], "node_id": "0067" }, { "title": "Probabilistic Generative Models", "start_index": 216, "end_index": 218, "nodes": [ { "title": "Continuous inputs", "start_index": 218, "end_index": 220, "node_id": "0076" }, { "title": "Maximum likelihood solution", "start_index": 220, "end_index": 222, "node_id": "0077" }, { "title": "Discrete features", "start_index": 222, "end_index": 222, "node_id": "0078" }, { "title": "Exponential family", "start_index": 222, "end_index": 223, "node_id": "0079" } ], "node_id": "0075" }, { "title": "Probabilistic Discriminative Models", "start_index": 223, "end_index": 224, "nodes": [ { "title": "Fixed basis functions", "start_index": 224, "end_index": 225, "node_id": "0081" }, { "title": "Logistic regression", "start_index": 225, "end_index": 227, "node_id": "0082" }, { "title": "Iterative reweighted least squares", "start_index": 227, "end_index": 229, "node_id": "0083" }, { "title": "Multiclass logistic regression", "start_index": 229, "end_index": 230, "node_id": "0084" }, { "title": "Probit regression", "start_index": 230, "end_index": 232, "node_id": "0085" }, { "title": "Canonical link functions", "start_index": 232, "end_index": 232, "node_id": "0086" } ], "node_id": "0080" }, { "title": "The Laplace Approximation", "start_index": 233, "end_index": 236, "nodes": [ { "title": "Model comparison and BIC", "start_index": 236, "end_index": 237, "node_id": "0088" } ], "node_id": "0087" }, { "title": "Bayesian Logistic Regression", "start_index": 237, "end_index": 237, "nodes": [ { "title": "Laplace approximation", "start_index": 237, "end_index": 238, "node_id": "0090" }, { "title": "Predictive distribution", "start_index": 238, "end_index": 240, "node_id": "0091" } ], "node_id": "0089" } ], "node_id": "0066" }, { "title": "Exercises", "start_index": 240, "end_index": 245, "node_id": "0092" }, { "title": "Neural Networks", "start_index": 245, "end_index": 247, "nodes": [ { "title": "Feed-forward Network Functions", "start_index": 247, "end_index": 251, "nodes": [ { "title": "Weight-space symmetries", "start_index": 251, "end_index": 252, "node_id": "0095" } ], "node_id": "0094" }, { "title": "Network Training", "start_index": 252, "end_index": 256, "nodes": [ { "title": "Parameter optimization", "start_index": 256, "end_index": 257, "node_id": "0097" }, { "title": "Local quadratic approximation", "start_index": 257, "end_index": 259, "node_id": "0098" }, { "title": "Use of gradient information", "start_index": 259, "end_index": 260, "node_id": "0099" }, { "title": "Gradient descent optimization", "start_index": 260, "end_index": 261, "node_id": "0100" } ], "node_id": "0096" }, { "title": "Error Backpropagation", "start_index": 261, "end_index": 262, "nodes": [ { "title": "Evaluation of error-function derivatives", "start_index": 262, "end_index": 265, "node_id": "0102" }, { "title": "A simple example", "start_index": 265, "end_index": 266, "node_id": "0103" }, { "title": "Efficiency of backpropagation", "start_index": 266, "end_index": 267, "node_id": "0104" }, { "title": "The Jacobian matrix", "start_index": 267, "end_index": 269, "node_id": "0105" } ], "node_id": "0101" }, { "title": "The Hessian Matrix", "start_index": 269, "end_index": 270, "nodes": [ { "title": "Diagonal approximation", "start_index": 270, "end_index": 271, "node_id": "0107" }, { "title": "Outer product approximation", "start_index": 271, "end_index": 272, "node_id": "0108" }, { "title": "Inverse Hessian", "start_index": 272, "end_index": 272, "node_id": "0109" }, { "title": "Finite differences", "start_index": 272, "end_index": 273, "node_id": "0110" }, { "title": "Exact evaluation of the Hessian", "start_index": 273, "end_index": 274, "node_id": "0111" }, { "title": "Fast multiplication by the Hessian", "start_index": 274, "end_index": 276, "node_id": "0112" } ], "node_id": "0106" }, { "title": "Regularization in Neural Networks", "start_index": 276, "end_index": 277, "nodes": [ { "title": "Consistent Gaussian priors", "start_index": 277, "end_index": 279, "node_id": "0114" }, { "title": "Early stopping", "start_index": 279, "end_index": 281, "node_id": "0115" }, { "title": "Invariances", "start_index": 281, "end_index": 283, "node_id": "0116" }, { "title": "Tangent propagation", "start_index": 283, "end_index": 285, "node_id": "0117" }, { "title": "Training with transformed data", "start_index": 285, "end_index": 287, "node_id": "0118" }, { "title": "Convolutional networks", "start_index": 287, "end_index": 289, "node_id": "0119" }, { "title": "Soft weight sharing", "start_index": 289, "end_index": 292, "node_id": "0120" } ], "node_id": "0113" }, { "title": "Mixture Density Networks", "start_index": 292, "end_index": 297, "node_id": "0121" }, { "title": "Bayesian Neural Networks", "start_index": 297, "end_index": 298, "nodes": [ { "title": "Posterior parameter distribution", "start_index": 298, "end_index": 300, "node_id": "0123" }, { "title": "Hyperparameter optimization", "start_index": 300, "end_index": 301, "node_id": "0124" }, { "title": "Bayesian neural networks for classification", "start_index": 301, "end_index": 304, "node_id": "0125" } ], "node_id": "0122" } ], "node_id": "0093" }, { "title": "Exercises", "start_index": 304, "end_index": 311, "node_id": "0126" }, { "title": "Kernel Methods", "start_index": 311, "end_index": 313, "nodes": [ { "title": "Dual Representations", "start_index": 313, "end_index": 314, "node_id": "0128" }, { "title": "Constructing Kernels", "start_index": 314, "end_index": 319, "node_id": "0129" }, { "title": "Radial Basis Function Networks", "start_index": 319, "end_index": 321, "nodes": [ { "title": "Nadaraya-Watson model", "start_index": 321, "end_index": 323, "node_id": "0131" } ], "node_id": "0130" }, { "title": "Gaussian Processes", "start_index": 323, "end_index": 324, "nodes": [ { "title": "Linear regression revisited", "start_index": 324, "end_index": 326, "node_id": "0133" }, { "title": "Gaussian processes for regression", "start_index": 326, "end_index": 331, "node_id": "0134" }, { "title": "Learning the hyperparameters", "start_index": 331, "end_index": 332, "node_id": "0135" }, { "title": "Automatic relevance determination", "start_index": 332, "end_index": 333, "node_id": "0136" }, { "title": "Gaussian processes for classification", "start_index": 333, "end_index": 335, "node_id": "0137" }, { "title": "Laplace approximation", "start_index": 335, "end_index": 339, "node_id": "0138" }, { "title": "Connection to neural networks", "start_index": 339, "end_index": 340, "node_id": "0139" } ], "node_id": "0132" } ], "node_id": "0127" }, { "title": "Exercises", "start_index": 340, "end_index": 344, "node_id": "0140" }, { "title": "Sparse Kernel Machines", "start_index": 345, "end_index": 346, "nodes": [ { "title": "Maximum Margin Classifiers", "start_index": 346, "end_index": 351, "nodes": [ { "title": "Overlapping class distributions", "start_index": 351, "end_index": 356, "node_id": "0143" }, { "title": "Relation to logistic regression", "start_index": 356, "end_index": 358, "node_id": "0144" }, { "title": "Multiclass SVMs", "start_index": 358, "end_index": 359, "node_id": "0145" }, { "title": "SVMs for regression", "start_index": 359, "end_index": 364, "node_id": "0146" }, { "title": "Computational learning theory", "start_index": 364, "end_index": 365, "node_id": "0147" } ], "node_id": "0142" }, { "title": "Relevance Vector Machines", "start_index": 365, "end_index": 365, "nodes": [ { "title": "RVM for regression", "start_index": 365, "end_index": 369, "node_id": "0149" }, { "title": "Analysis of sparsity", "start_index": 369, "end_index": 373, "node_id": "0150" }, { "title": "RVM for classification", "start_index": 373, "end_index": 377, "node_id": "0151" } ], "node_id": "0148" } ], "node_id": "0141" }, { "title": "Exercises", "start_index": 377, "end_index": 379, "node_id": "0152" }, { "title": "Graphical Models", "start_index": 379, "end_index": 380, "nodes": [ { "title": "Bayesian Networks", "start_index": 380, "end_index": 382, "nodes": [ { "title": "Example: Polynomial regression", "start_index": 382, "end_index": 385, "node_id": "0155" }, { "title": "Generative models", "start_index": 385, "end_index": 386, "node_id": "0156" }, { "title": "Discrete variables", "start_index": 386, "end_index": 390, "node_id": "0157" }, { "title": "Linear-Gaussian models", "start_index": 390, "end_index": 392, "node_id": "0158" } ], "node_id": "0154" }, { "title": "Conditional Independence", "start_index": 392, "end_index": 393, "nodes": [ { "title": "Three example graphs", "start_index": 393, "end_index": 398, "node_id": "0160" }, { "title": "D-separation", "start_index": 398, "end_index": 403, "node_id": "0161" } ], "node_id": "0159" }, { "title": "Markov Random Fields", "start_index": 403, "end_index": 403, "nodes": [ { "title": "Conditional independence properties", "start_index": 403, "end_index": 404, "node_id": "0163" }, { "title": "Factorization properties", "start_index": 404, "end_index": 407, "node_id": "0164" }, { "title": "Illustration: Image de-noising", "start_index": 407, "end_index": 410, "node_id": "0165" }, { "title": "Relation to directed graphs", "start_index": 410, "end_index": 413, "node_id": "0166" } ], "node_id": "0162" }, { "title": "Inference in Graphical Models", "start_index": 413, "end_index": 414, "nodes": [ { "title": "Inference on a chain", "start_index": 414, "end_index": 418, "node_id": "0168" }, { "title": "Trees", "start_index": 418, "end_index": 419, "node_id": "0169" }, { "title": "Factor graphs", "start_index": 419, "end_index": 422, "node_id": "0170" }, { "title": "The sum-product algorithm", "start_index": 422, "end_index": 431, "node_id": "0171" }, { "title": "The max-sum algorithm", "start_index": 431, "end_index": 436, "node_id": "0172" }, { "title": "Exact inference in general graphs", "start_index": 436, "end_index": 437, "node_id": "0173" }, { "title": "Loopy belief propagation", "start_index": 437, "end_index": 438, "node_id": "0174" }, { "title": "Learning the graph structure", "start_index": 438, "end_index": 438, "node_id": "0175" } ], "node_id": "0167" } ], "node_id": "0153" }, { "title": "Exercises", "start_index": 438, "end_index": 443, "node_id": "0176" }, { "title": "Mixture Models and EM", "start_index": 443, "end_index": 444, "nodes": [ { "title": "K-means Clustering", "start_index": 444, "end_index": 448, "nodes": [ { "title": "Image segmentation and compression", "start_index": 448, "end_index": 450, "node_id": "0179" } ], "node_id": "0178" }, { "title": "Mixtures of Gaussians", "start_index": 450, "end_index": 452, "nodes": [ { "title": "Maximum likelihood", "start_index": 452, "end_index": 455, "node_id": "0181" }, { "title": "EM for Gaussian mixtures", "start_index": 455, "end_index": 459, "node_id": "0182" } ], "node_id": "0180" }, { "title": "An Alternative View of EM", "start_index": 459, "end_index": 461, "nodes": [ { "title": "Gaussian mixtures revisited", "start_index": 461, "end_index": 463, "node_id": "0184" }, { "title": "Relation to K-means", "start_index": 463, "end_index": 464, "node_id": "0185" }, { "title": "Mixtures of Bernoulli distributions", "start_index": 464, "end_index": 468, "node_id": "0186" }, { "title": "EM for Bayesian linear regression", "start_index": 468, "end_index": 470, "node_id": "0187" } ], "node_id": "0183" }, { "title": "The EM Algorithm in General", "start_index": 470, "end_index": 475, "node_id": "0188" } ], "node_id": "0177" }, { "title": "Exercises", "start_index": 475, "end_index": 480, "node_id": "0189" }, { "title": "Approximate Inference", "start_index": 481, "end_index": 482, "nodes": [ { "title": "Variational Inference", "start_index": 482, "end_index": 484, "nodes": [ { "title": "Factorized distributions", "start_index": 484, "end_index": 486, "node_id": "0192" }, { "title": "Properties of factorized approximations", "start_index": 486, "end_index": 490, "node_id": "0193" }, { "title": "Example: The univariate Gaussian", "start_index": 490, "end_index": 493, "node_id": "0194" }, { "title": "Model comparison", "start_index": 493, "end_index": 494, "node_id": "0195" } ], "node_id": "0191" }, { "title": "Illustration: Variational Mixture of Gaussians", "start_index": 494, "end_index": 495, "nodes": [ { "title": "Variational distribution", "start_index": 495, "end_index": 501, "node_id": "0197" }, { "title": "Variational lower bound", "start_index": 501, "end_index": 502, "node_id": "0198" }, { "title": "Predictive density", "start_index": 502, "end_index": 503, "node_id": "0199" }, { "title": "Determining the number of components", "start_index": 503, "end_index": 505, "node_id": "0200" }, { "title": "Induced factorizations", "start_index": 505, "end_index": 506, "node_id": "0201" } ], "node_id": "0196" }, { "title": "Variational Linear Regression", "start_index": 506, "end_index": 506, "nodes": [ { "title": "Variational distribution", "start_index": 506, "end_index": 508, "node_id": "0203" }, { "title": "Predictive distribution", "start_index": 508, "end_index": 509, "node_id": "0204" }, { "title": "Lower bound", "start_index": 509, "end_index": 510, "node_id": "0205" } ], "node_id": "0202" }, { "title": "Exponential Family Distributions", "start_index": 510, "end_index": 511, "nodes": [ { "title": "Variational message passing", "start_index": 511, "end_index": 512, "node_id": "0207" } ], "node_id": "0206" }, { "title": "Local Variational Methods", "start_index": 513, "end_index": 518, "node_id": "0208" }, { "title": "Variational Logistic Regression", "start_index": 518, "end_index": 518, "nodes": [ { "title": "Variational posterior distribution", "start_index": 518, "end_index": 520, "node_id": "0210" }, { "title": "Optimizing the variational parameters", "start_index": 520, "end_index": 522, "node_id": "0211" }, { "title": "Inference of hyperparameters", "start_index": 522, "end_index": 525, "node_id": "0212" } ], "node_id": "0209" }, { "title": "Expectation Propagation", "start_index": 525, "end_index": 531, "nodes": [ { "title": "Example: The clutter problem", "start_index": 531, "end_index": 533, "node_id": "0214" }, { "title": "Expectation propagation on graphs", "start_index": 533, "end_index": 537, "node_id": "0215" } ], "node_id": "0213" } ], "node_id": "0190" }, { "title": "Exercises", "start_index": 537, "end_index": 542, "node_id": "0216" }, { "title": "Sampling Methods", "start_index": 543, "end_index": 546, "nodes": [ { "title": "Basic Sampling Algorithms", "start_index": 546, "end_index": 546, "nodes": [ { "title": "Standard distributions", "start_index": 546, "end_index": 548, "node_id": "0219" }, { "title": "Rejection sampling", "start_index": 548, "end_index": 550, "node_id": "0220" }, { "title": "Adaptive rejection sampling", "start_index": 550, "end_index": 552, "node_id": "0221" }, { "title": "Importance sampling", "start_index": 552, "end_index": 554, "node_id": "0222" }, { "title": "Sampling-importance-resampling", "start_index": 554, "end_index": 556, "node_id": "0223" }, { "title": "Sampling and the EM algorithm", "start_index": 556, "end_index": 556, "node_id": "0224" } ], "node_id": "0218" }, { "title": "Markov Chain Monte Carlo", "start_index": 557, "end_index": 559, "nodes": [ { "title": "Markov chains", "start_index": 559, "end_index": 561, "node_id": "0226" }, { "title": "The Metropolis-Hastings algorithm", "start_index": 561, "end_index": 562, "node_id": "0227" } ], "node_id": "0225" }, { "title": "Gibbs Sampling", "start_index": 562, "end_index": 566, "node_id": "0228" }, { "title": "Slice Sampling", "start_index": 566, "end_index": 568, "node_id": "0229" }, { "title": "The Hybrid Monte Carlo Algorithm", "start_index": 568, "end_index": 568, "nodes": [ { "title": "Dynamical systems", "start_index": 568, "end_index": 572, "node_id": "0231" }, { "title": "Hybrid Monte Carlo", "start_index": 572, "end_index": 574, "node_id": "0232" } ], "node_id": "0230" }, { "title": "Estimating the Partition Function", "start_index": 574, "end_index": 576, "node_id": "0233" } ], "node_id": "0217" }, { "title": "Exercises", "start_index": 576, "end_index": 579, "node_id": "0234" }, { "title": "Continuous Latent Variables", "start_index": 579, "end_index": 581, "nodes": [ { "title": "Principal Component Analysis", "start_index": 581, "end_index": 581, "nodes": [ { "title": "Maximum variance formulation", "start_index": 581, "end_index": 583, "node_id": "0237" }, { "title": "Minimum-error formulation", "start_index": 583, "end_index": 585, "node_id": "0238" }, { "title": "Applications of PCA", "start_index": 585, "end_index": 589, "node_id": "0239" }, { "title": "PCA for high-dimensional data", "start_index": 589, "end_index": 590, "node_id": "0240" } ], "node_id": "0236" }, { "title": "Probabilistic PCA", "start_index": 590, "end_index": 594, "nodes": [ { "title": "Maximum likelihood PCA", "start_index": 594, "end_index": 597, "node_id": "0242" }, { "title": "EM algorithm for PCA", "start_index": 597, "end_index": 600, "node_id": "0243" }, { "title": "Bayesian PCA", "start_index": 600, "end_index": 603, "node_id": "0244" }, { "title": "Factor analysis", "start_index": 603, "end_index": 606, "node_id": "0245" } ], "node_id": "0241" }, { "title": "Kernel PCA", "start_index": 606, "end_index": 610, "node_id": "0246" }, { "title": "Nonlinear Latent Variable Models", "start_index": 611, "end_index": 611, "nodes": [ { "title": "Independent component analysis", "start_index": 611, "end_index": 612, "node_id": "0248" }, { "title": "Autoassociative neural networks", "start_index": 612, "end_index": 615, "node_id": "0249" }, { "title": "Modelling nonlinear manifolds", "start_index": 615, "end_index": 619, "node_id": "0250" } ], "node_id": "0247" } ], "node_id": "0235" }, { "title": "Exercises", "start_index": 619, "end_index": 624, "node_id": "0251" }, { "title": "Sequential Data", "start_index": 625, "end_index": 627, "nodes": [ { "title": "Markov Models", "start_index": 627, "end_index": 630, "node_id": "0253" }, { "title": "Hidden Markov Models", "start_index": 630, "end_index": 635, "nodes": [ { "title": "Maximum likelihood for the HMM", "start_index": 635, "end_index": 638, "node_id": "0255" }, { "title": "The forward-backward algorithm", "start_index": 638, "end_index": 645, "node_id": "0256" }, { "title": "The sum-product algorithm for the HMM", "start_index": 645, "end_index": 647, "node_id": "0257" }, { "title": "Scaling factors", "start_index": 647, "end_index": 649, "node_id": "0258" }, { "title": "The Viterbi algorithm", "start_index": 649, "end_index": 651, "node_id": "0259" }, { "title": "Extensions of the hidden Markov model", "start_index": 651, "end_index": 655, "node_id": "0260" } ], "node_id": "0254" }, { "title": "Linear Dynamical Systems", "start_index": 655, "end_index": 658, "nodes": [ { "title": "Inference in LDS", "start_index": 658, "end_index": 662, "node_id": "0262" }, { "title": "Learning in LDS", "start_index": 662, "end_index": 664, "node_id": "0263" }, { "title": "Extensions of LDS", "start_index": 664, "end_index": 665, "node_id": "0264" }, { "title": "Particle filters", "start_index": 665, "end_index": 666, "node_id": "0265" } ], "node_id": "0261" } ], "node_id": "0252" }, { "title": "Exercises", "start_index": 666, "end_index": 672, "node_id": "0266" }, { "title": "Combining Models", "start_index": 673, "end_index": 674, "nodes": [ { "title": "Bayesian Model Averaging", "start_index": 674, "end_index": 675, "node_id": "0268" }, { "title": "Committees", "start_index": 675, "end_index": 677, "node_id": "0269" }, { "title": "Boosting", "start_index": 677, "end_index": 679, "nodes": [ { "title": "Minimizing exponential error", "start_index": 679, "end_index": 681, "node_id": "0271" }, { "title": "Error functions for boosting", "start_index": 681, "end_index": 683, "node_id": "0272" } ], "node_id": "0270" }, { "title": "Tree-based Models", "start_index": 683, "end_index": 686, "node_id": "0273" }, { "title": "Conditional Mixture Models", "start_index": 686, "end_index": 687, "nodes": [ { "title": "Mixtures of linear regression models", "start_index": 687, "end_index": 690, "node_id": "0275" }, { "title": "Mixtures of logistic models", "start_index": 690, "end_index": 692, "node_id": "0276" }, { "title": "Mixtures of experts", "start_index": 692, "end_index": 694, "node_id": "0277" } ], "node_id": "0274" } ], "node_id": "0267" }, { "title": "Exercises", "start_index": 694, "end_index": 696, "node_id": "0278" }, { "title": "Appendix A Data Sets", "start_index": 697, "end_index": 704, "node_id": "0279" }, { "title": "Appendix B Probability Distributions", "start_index": 705, "end_index": 714, "node_id": "0280" }, { "title": "Appendix C Properties of Matrices", "start_index": 715, "end_index": 722, "node_id": "0281" }, { "title": "Appendix D Calculus of Variations", "start_index": 723, "end_index": 726, "node_id": "0282" }, { "title": "Appendix E Lagrange Multipliers", "start_index": 727, "end_index": 730, "node_id": "0283" }, { "title": "References", "start_index": 731, "end_index": 749, "node_id": "0284" }, { "title": "Index", "start_index": 749, "end_index": 758, "node_id": "0285" } ] }