Unit 05 | Probabilistic Learning: Classification with Naive Bayes |
| 10 hrs |
Upon completion of this module, you will be able to:
- explain the Naive Bayes algorithm for probabilistic classification
- estimate probabilities through frequency distributions
- apply Naive Bayes to classification problems
- implement Naive Bayes in R through code and through packages
- engineer and transform features for use in algorithms
Essential Concepts of Probability
|
Required Work
Additional ResourcesSlide Deck & Data Sets
|
Understanding Naive Bayes
Slide Deck & Data Sets |
Required Work
Additional Resources |
Guest Lecture: Naive Bayes Classification Algorithm
|
Required Work
Additional Resources
|
Feature Engineering
|
Required Work
Additional ResourcesData Sets
|
Applying Naive Bayes
|
Required WorkIn this lesson we'll take a look at various applications of the Naive Bayes algorithm for classification. One of the guest lectures compares Naive Bayes and kNN. In addition, there's a link of a research paper below that compares kNN and Naive Bayes in clinical use. Lastly, there's a short tutorial on k-fold cross validation, a common technique for validating models. We will return to that technique later in the course again but it's worth to start thinking about it.
Additional Resources
|