Difference between revisions of "10-601 Classification and K-NN"
From Cohen Courses
Jump to navigationJump to search| Line 14: | Line 14: | ||
* What is the goal of classification | * What is the goal of classification | ||
| − | * | + | * What sorts of problems can be solved by reducing them to classification |
| − | |||
* What the K-NN algorithm is. | * What the K-NN algorithm is. | ||
| − | |||
| − | |||
| − | |||
* How the value of K affects the tendency of K-NN to overfit or underfit data. | * How the value of K affects the tendency of K-NN to overfit or underfit data. | ||
| − | * | + | |
| + | * Optional: | ||
| + | ** Bayes decision boundary for classification | ||
| + | ** Is there an optimal classifier? | ||
| + | ** ''What decision boundary is defined by K-NN, and how it compares to decision boundaries of linear classifiers.'' | ||
| + | ** Probabilistic interpretation of KNN decisions | ||
Revision as of 10:35, 16 September 2014
This a lecture used in the Syllabus for Machine Learning 10-601 in Fall 2014
Slides
- Ziv's lecture: Slides in pdf.
- William's lecture (draft): Slides in Powerpoint.
Readings
- Mitchell, Chapters 1,2 and 8.
What You Should Know Afterward
- What is the goal of classification
- What sorts of problems can be solved by reducing them to classification
- What the K-NN algorithm is.
- How the value of K affects the tendency of K-NN to overfit or underfit data.
- Optional:
- Bayes decision boundary for classification
- Is there an optimal classifier?
- What decision boundary is defined by K-NN, and how it compares to decision boundaries of linear classifiers.
- Probabilistic interpretation of KNN decisions
