Introduction to the theory and algorithms of statistical pattern recognition with applications to recognition of sounds (e.g. speech, music), visual objects, audio-visual events, and other spatio-temporal sensory or symbolic data. Bayesian decision and estimation theory (Maximum Likelihood, Maximum-A-Posteriori). Nearest neighbor decision rule. Methods for clustering (e.g. k-means) and unsupervised learning. Decision trees. Methods for feature transformation and selection in pattern space, and dimensionality reduction: principal component analysis (PCA), linear discriminant analysis (LDA), independent component analysis (ICA). Methods for linear and nonlinear regression. Pattern classification methods with linear discriminant machines: Perceptrons και Support Vector Machines. Hidden Markov models (HMMs), Gaussian Mixture models (GMMs), Expectation-Maximization algorithm, Viterbi algorithm. Dynamic Bayesian nets. Probabilistic graphical models. Deep learning methods: Deep, Convolutional, Recursive Neural Nets (DNNs CNNs, RNNs). Analytic and laboratory exercises.