Bayesian Networks 3 – Maximum Likelihood – Stanford CS221: AI (Autumn 2019)

Stanford University via YouTube

YouTube based on 0 ratings

Likes

Overview

Bayesian Networks 3 - Maximum Likelihood is an advanced module from Stanford’s CS221 Artificial Intelligence course (Autumn 2019) that focuses on parameter learning in Bayesian networks using the Maximum Likelihood Estimation (MLE) approach. This module builds on previous topics covering Bayesian network structure and inference, emphasizing how to learn the model parameters from data. You will explore how MLE is used to find the best-fitting parameters that maximize the likelihood of observed data under the Bayesian network model. The course explains...

Syllabus

Introduction. Announcements. Review: Bayesian network. Review: probabilistic inference. Where do parameters come from?. Roadmap. Learning task. Example: one variable. Example: v-structure. Example: inverted-v structure. Parameter sharing. Example: Naive Bayes. Example: HMMS. General case: learning algorithm. Maximum likelihood. Scenario 2. Regularization: Laplace smoothing. Example: two variables. Motivation. Maximum marginal likelihood. Expectation Maximization (EM).