Bayesian parameter estimation, output prediction, state estimationess, regression model, state space model, estimation, application of dynamic models.
Abstract:
System. Regression, discrete and logistic models. Bayesian estimation of model parameters. Parameter estimation of normal regression, discrete and logistic models. Classification with logistic model. One-step and multi-step prediction with regression and discrete models. State model. State estimation. Kalman filter. Control with regression and discrete models.
Objectives:
Teach students advanced methods for analyzing the behavior of dynamical systems, including system identification and output prediction for continuous and discrete random variables based on Bayesian statistics.