Mining Data from Variable Dependencies

This course will teach you several models like Bayesian Networks, LBP, Variable Elimination, etc. with the help of which you can derive complex relationships across multiple input variables or features.

Mining data involves deriving complex probabilistic relationships between multiple variables. In this course, Mining Data from Variable Dependencies, you’ll learn to apply probabilistic graph models to derive complex relationships across variables/features. First, you’ll explore Bayesian Networks. Next, you’ll discover D Separation. Finally, you’ll learn how to perform data fragmentation. When you’re finished with this course, you’ll have the skills and knowledge of Python Probabilistic models needed to explore relationships across variables/input features to derive joint probabilities, or impact of features on the final outcome.

• Course Overview 1min
• Understanding Probability in the Context of Sports 14mins
• Finding Connected Variables Using Bayesian Networks 32mins
• Extracting Relationships Using Structured Learning 22mins
• Estimating Parameter Distributions to Improve the Model 33mins
• Detecting Anomalous Events Over Time 15mins