[1] What are ML algorithms, how did they come about, where are they today, what to expect in 5-10 years. Computational foundations, societal impact. Refresher (test?) of basics of descriptive statistics, linear algebra, optimization, information theory.
[2] Data collection, standard data sets, repositories. Survey of major application domains: speech- and character recognition (ASR, OCR), (biometric) identification, pattern classification, ranking/recommendation, info extraction, info retrieval, natural language processing (NLP).
[3] Principal component analysis, linear discriminant analysis, max margin classifiers, data reduction, feature engineering.
[4] Maximum entropy methods, decision trees.
[5] Genetic/evolutionary methods, boosting
[6] Midterm exam
[7] Nearest neighbor, tangent distance methods.
[8] Algorithmic information theory, Kolmogorov complexity, minimum description length.
[9] Hidden Markov Models (HMM), Viterbi, EM.
[10] Learning with multiple goals.
[11] Neural nets (NN), backpropagation.
[12] Final exam