- Supervised vs Unsupervised
- Bias vs Variance
- Underfitting vs overfitting
- Tackle overfitting
- L1 regulariziation
- L2 regularization
- L1 (Lasso) vs L2 (Ridge)
- Dropout
- Why feature reduction / dimensionality reduction
- How feature reduction / dimensionality reduction
- AUC ROC
- No Free Lunch Theorum
- Empirical Risk
- Class imbalance tackle
- Selection bias
- What is random forest? Why "random"?
- Decision trees vs Logisitc regression
- SVM vs Logistic Regression
- Kernel trick
- Primal vs Dual version of classifier
- Parametric vs Non-parametric
- KNN
- KMeans
- KNN vs Kmeans
- Smoothing Time series
- Gradient descent
- Backpropagation
- Regularization
- Normalization
- Batch Normalization
- Vanishing Gradients
- Exploding gradients
- Dimensionality reduction
- PCA
- Kernel PCA
- Ridge regression
- L1 vs L2 loss
- Activation Functions
- Advantages of RelU
- Thresholds for a classifier
- Interpretation of an ROC area under the curve as an integral
- Confusion matrix