1. What is the difference between supervised and semi-supervised learning?
2. What are the advantages of using SVM over a simple linear classifier?
3. How do you interpret the coefficients of a logistic regression model?
4. What is multi-class classification, and how is it handled in logistic regression?
5. What are the key assumptions behind linear regression?
6. How does gradient descent work, and how does it converge?
7. What are the different types of gradient descent?
8. What is the difference between Ridge and Lasso regression?
9. What is elastic net regularization, and when should it be used?
10. How does the curse of dimensionality affect machine learning algorithms?
11. What is the role of eigenvalues and eigenvectors in PCA?
12. How do you choose the number of principal components in PCA?
13. What is the difference between K-means and hierarchical clustering?
14. What is the purpose of the inertia metric in K-means clustering?
15. How do you handle missing data in machine learning?
16. What is the concept of cross-entropy loss in classification problems?
17. What is the softmax function, and why is it used in multi-class classification?
18. What is the significance of the learning rate in gradient-based optimization algorithms?
19. How do you prevent overfitting in machine learning models?
20. How does dropout work in neural networks, and why is it effective?
21. What is the purpose of using early stopping in training neural networks?
22. How do you balance bias and variance in a machine learning model?
23. What are ensemble methods, and how do they improve model performance?
24. How does bagging reduce variance in machine learning models?
25. How does boosting reduce bias in machine learning models?
26. What is the difference between AdaBoost and Gradient Boosting?
27. How does XGBoost differ from traditional gradient boosting?
28. What is LightGBM, and what makes it efficient compared to XGBoost?
29. What is CatBoost, and why is it suitable for categorical features?
30. How do decision trees handle both categorical and numerical data?
31. What is information gain, and how is it used in decision trees?
32. What is the Gini index, and how is it used in decision trees?
33. How does Random Forest improve over a single decision tree?
34. What is feature importance, and how is it computed in Random Forests?
35. How does feature selection impact model performance?
36. What is the purpose of one-hot encoding, and when should it be used?
37. What is label encoding, and when is it preferred over one-hot encoding?
38. How does k-fold cross-validation work?
39. What is stratified cross-validation, and when should it be used?
40. How does Leave-One-Out cross-validation (LOOCV) differ from k-fold cross-validation?