Introduction to Data Science and Machine Learning

Revision of continuous random variables, multivariate distributions, marginalization, conditional distributions; Charts and data visualization, including bar charts, line charts, error bars, pie charts, scatter plots, bubble charts, box plots, chart information elements, coherence and aesthetics; Exploratory data analysis, including statistical descriptors, correlations, QQ plots; Hypothesis testing, t-test, chi-squared test, non-parametric tests; Linear and logistic regression, derivation of loss functions, gradient descent, L2 and L1 regularization, validation, cross-validation, domain shift; Support vector machines and kernel methods for classification and regression; Shallow neural networks, importance of hidden layer, computation graphs and Jacobians, backpropagation; Feature engineering, imputation, forward selection, backward elimination; Combining models, ensembles, cascades and trees, random forests, boosting; Clustering, k-means, fuzzy c-means, DBSCAN, hierarchical, clustering metrics; Dimensionreduction, PCA, kernel PCA, t-SNE. Density estimation, maximum likelihood parameter estimate, kernel density estimation, EM-algorithm for GMM.