AMT 459 2.0 Mathematics of Machine Learning

Course: AMT 459 2.0 Mathematics of Machine Learning (Optional)

Course content:

PAC learning model, learning via uniform convergence, The Bias-Complexity Tradeoff, The VC-dimension and the Fundamental Theorem of Statistical Learning, Linear Predictors and Boosting, Non-uniform Learnability, Model selection and validation, Convex Learning problems, Regularization and Stability, Stochastic gradient descent, Support vector machines, Kernel methods, Decision trees, Clustering and dimension reduction, Generative Models, Feature selection and generation.

Recommended Readings:

    1. Shai Ben-David and Shai Shalev-Shwartz, Understanding Machine Learning: From Theory to Algorithms, Cambridge University Press, 2014
    2. Trevor Hastie, Robert Tibshirani and Jerome Friedman, The Elements of Statistical Learning: Data Mining, Inference, and Prediction, Second Edition, Springer Series in Statistics 2016.