SVM
Back to Home
01. Welcome to SVM
02. Separating Line
03. Choosing Between Separating Lines
04. What Makes A Good Separating Line
05. Practice with Margins
06. SVMs and Tricky Data Distributions
07. SVM Response to Outliers
08. SVM Outlier Practice
09. Handoff to Katie
10. SVM in SKlearn
11. SVM Decision Boundary
12. Coding Up the SVM
13. Nonlinear SVMs
14. Nonlinear Data
15. A New Feature
16. Visualizing the New Feature
17. Separating with the New Feature
18. Practice Making a New Feature
19. Kernel Trick
20. Playing Around with Kernel Choices
21. Kernel and Gamma
22. SVM C Parameter
23. SVM Gamma Parameter
24. Overfitting
25. SVM Strengths and Weaknesses
26. SVM Mini-Project Video
27. SVM Mini-Project
28. SVM Author ID Accuracy
29. SVM Author ID Timing
30. A Smaller Training Set
31. Speed-Accuracy Tradeoff
32. Deploy an RBF Kernel
33. Optimize C Parameter
34. Accuracy after Optimizing C
35. Optimized RBF vs. Linear SVM: Accuracy
36. Extracting Predictions from an SVM
37. How Many Chris Emails Predicted?
38. Final Thoughts on Deploying SVMs
Back to Home
16. Visualizing the New Feature
Visualizing the New Feature
Next Concept