New courses in Media Arts and Sciences http://ocw.mit.edu/OcwWeb/Media-Arts-and-Sciences/index.htm 2008-01-18 MIT OpenCourseWare http://ocw.mit.edu en-US Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see http://ocw.mit.edu/OcwWeb/web/terms/terms/index.htm Fundamentals of characterizing and recognizing patterns and features of interest in numerical data. Basic tools and theory for signal understanding problems with applications to user modeling, affect recognition, speech recognition and understanding, computer vision, physiological analysis, and more. Decision theory, statistical classification, maximum likelihood and Bayesian estimation, non-parametric methods, unsupervised learning and clustering. Additional topics on machine and human learning from active research. http://ocw.mit.edu/OcwWeb/Media-Arts-and-Sciences/MAS-622JFall-2006/CourseHome/index.htm Picard, Rosalind Thomaz, Andrea Morgan, Bo 2007-10-05T02:20:22-04:00 MAS.622J 1.126J en-US Civil and Environmental Engineering Cognitive Psychology and Psycholinguistics genetic algorithms reinforcement learning decision trees Bayesian networks Kalman filtering linear dynamical systems Baum-Welch algorithm viterbi algorithm Hidden markov models Expectation-Maximization K-means vector quantization clustering unsupervised learning parzen estimation K-nearest-neighbor classification support vecotr machines optimization by gradient descent perceptron learning linear discriminant eigenvector and multilinear analysis feature extraction template-based recognition fisher discriminant likelihood ratio test ROC curves random vectors, decision theory bayes rule conditional probability pattern analysis probability theory classification feature detection pattern recognition Media Arts and Sciences MIT Open Course Ware http://ocw.mit.edu Content within individual OCW courses is (c) by the individual authors unless otherwise noted. MIT OpenCourseWare materials are licensed by the Massachusetts Institute of Technology under a Creative Commons License (Attribution-NonCommercial-ShareAlike). For further information see http://ocw.mit.edu/OcwWeb/web/terms/terms/index.htm