HCS6349 - Statistical Machine Learning for Artificial Neural Nets

HCS 6349 (ACN 6349) Statistical Machine Learning for Artificial Neural Nets (3 semester credit hours) Mathematical tools for investigating the asymptotic behavior of both batch and adaptive machine learning algorithms including the Invariant Set Theorem, 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 the theory to unsupervised, supervised, and reinforcement learning machines and artificial neural network modeling. Prerequisites: (ACN 6348 or HCS 6348) and BBSC majors only and department consent required. (3-0) T