Math 466

THIS SYLLABUS IS STILL A DRAFT AND SUBJECT TO REVISION

Intro to ML (1 Lecture)
Topics: Regression & Classification, Supervised & Unsupervised Learning, Training, Test, and Validation Data, Bias-Variance Tradeoff, Model Complexity, Sensitivity, Specificity, TF, FP.

Statistical Learning Theory (2 Lectures)
Topics: Empirical Risk Minimization, Hypothesis Classes, PAC Learnability, No Free Lunch Theorem, Ugly Duckling Theorem, VC Dimension.

Tree Models (2 Lectures)
Topics: Decision, Regression, and Classification Trees, Purity Measures, Feature Importance, CART, Pruning, Boostrap, Bagging, Random Forest, Boosting, AdaBoost.

Dimensionality Reduction (2 Lectures)
Topics: Curse and Blessing of Dimensionality, PCA, Kernel PCA, LLE, MDS, Random Projections, Johnson-Lindenstrauss, Isomap, Laplacian Eigenmaps.

Optimization Theory (4 Lectures)
Topics: Convex Geometry, Convex Functions, 1st and 2nd Order Conditions for Convexity, Convex Optimization, Logistic Regression, SVM, Linear Search, Gradient Descent, Newton’s Method, Subgradients, SGD, Momentum.

Intro to NN (2 Lectures)
Topics: Components of Neural Networks, Backprop, Cross-Entropy, Regularization, Dropout, Weight Initilization, Vanishing/Exploding Gradients, Universal Approximation Theorem.

Convolutional Neural Networks (2 Lectures)
Topics: Filters, Pooling, Convolution, Stride, Boundary, Translation Equivariance, Reduction of Complexity, CNN + GANs, CNN on Graphs.

Representation Learning (2 Lectures)
Topics: Window Co-Occurence, CBOW, Skip-Gram, RNNs, Information Theory, Hierarchical Softmax, Sentiment Analysis, Various Autoencoder Architectures.

Reinforcement Learning (4 Lectures)
Topics: k-Bandit Problem, Greed vs. Exploration, Environments, States, Actions, Rewads, Agents, Policies, Value Functions, Bellman Equations, Policy Evaluation, Policy Iteration, Optimality Equations, Convergence Theorems, Monte-Carlo Methods, Temporal-Difference Methods.

%d bloggers like this: