HCS6349 - Statistical Machine Learning with Deep Learning Applications

HCS 6349 (ACN 6349) Statistical Machine Learning with Deep Learning Applications (3 semester credit hours) Mathematical tools for investigating the asymptotic behavior of both batch and adaptive machine learning algorithms including the Zoutendijk-Wolfe convergence theorem, adaptive stochastic approximation methods, and Monte Carlo Markov Chain methods. M-estimation and bootstrap asymptotic statistical theory for characterizing asymptotic behavior of parameter estimates as a function of sample size to support: model selection, specification analysis, and hypothesis testing. Emphasizes applications of theory to unsupervised, supervised, and reinforcement learning machines and deep learning. Prerequisites: (ACN 6348 or HCS 6348) and department consent required. (3-0) T