Here is a selected list of classes that I have either taken or audited. Other than the courses listed below, please note that I have also independently studied a number of research papers on contemporary techniques in Computer Vision, Statistical Learning and Machine Learning.
Image Understanding (CS216) -- Computer Vision Class
Topics: Linear Filters, Edge Detection (Gaussian Derivates, Gabor Filtes, Steerable Filters, Gradients) , Template Based Detection, Binary Images (morphology) Fitting (Line Fitting, Hough Transforms, Ransac), Texture, Segementation (Clustering, Markov Random Fields, Graph Cut, Mixture Models, Normalized Cut), Recognition (Digit Recognition, SVM's, boosting), Deformable Matching (Active Appearance Models), Manifolds, Pictorial Structures, Discriminative Parts Models, Video (optical flow, tracking), 3D representation.
Topics: Classification - Decision Trees, random Forests, Boosting, k-Nearest Neighbors, Naive Bayes, over-fitting, bias-variance tradeoff, crossvalidation, Neural Networks, Perceptron, Logistic Regression, Multi-layer Networks, Back-Propagation, Kernel Methods, Support Vector Machines, Clustering, Dimensionality Reduction, kernel Principal Component Analysis, Kernel Design, Non-linear Dimension Reduction, Kernel Fisher Linear Discriminant Analysis, Kernel Canonical Correlation Analysis, Algorithm Evaluation, Hypothesis Testing.
Also, I heavily used Professor Andrew Ng's Machine Learning Class Youtube videos.
Topics: Data Measurement, Exploratory Data Mining, Data Visualization, Predictive Modeling - Classification and Regression, Model Fitting as optimization, Predictive Performance evaluation, Overfitting, Regularization, Clustering, Text Mining - Topic Modeling, Text Classification, Search, Graphical Modeling, Unsupervised Learning. Recommender Systems - Nearest neighbor algorithms, Matrix decomposition, Collaborative Filtering, Evaluating Recommender Systems. Web Data Analysis - Web Search Basics, PageRank, Eigenvector Methods for web information retrieval, Link Analysis of a web graph, Learning with Clickthrough data. Social Network Analysis - Social Network Analysis, Network Embedding and latent space models, Network Data over time, Link prediction. Time Series Analysis and Anomaly Detection - Basic Concepts of Time Series analysis, Principles of Markov and Hidden Markov Models, Event Data and Poisson Modeling, Techniques for detecting anomalies, events (Poisson-Markov event detection), motifs etc.
Probabilistic Learning (CS274a)
Topics: Frequentist vs. Bayesian viewpoints, Conditional Independence, Graphical Models, multivariate Gaussians, Likelihood, Maximum Likelihood Learning (Univariate ML, Bias, variance, multivariate, exponential family), Bayesian Learning (priors, posterior distributions, MAP and MPE estimation, conjugate priors, beta-binomial, Gaussian Models, Baye's optimal decisions), Classification and Regression as parameter estimation problems, Bias/Variance and Bayesian Priors for regression, Logistic Regression, Mixture Models and Expectation Maximization, Complexity and Model Selection, Marginal Likelihood, Latent Space Representation, Principal Component Analysis (PCA), Probabilistic PCA, Hidden Markov Models, Monte Carlo Methods.
Topics: Functional Analysis, Abstract Spaces (Hilbert Spaces, Banach Spaces), Computational Linear Algebra (iterative and direct methods, eigenproblems, matrix factorizations), Approximation Methods (linear least squares, radial basis functions, projection methods, splines), optimization methods (gradient descent, Newton's method, linear-programming, quadratic programming, semi-definite programming), Numerical Integration and Differentation, Fast Fourier Transforms, Discrete Sine and Cosine Transforms, Convolutions, Polynomial Multiplication, Partial Differential Equations (Finite difference methods, Solving Laplace's and Poisson's equations) .
Light and Geometry in Vision (CS217)
Topics: Cameras (Pinhole mode, Thin Lens optics, Geometric models, calibration), Projective Geometry (Homogenous coordinates, Homographies), Multiview Geometry (Triangulation, Epipolar Constraints, 8 point algorithm), Structure from Motion (Stratified reconstruction, bundle adjustment, feature correspondence, RANSAC), Stereo (Rectification, Matching, Dynamic Programming), Light Transport (Color, Radiometry, global Illumination) Photometric Stereo, Shape from shading and specularities.