Supervised Learning

Linear/logistic regression, SVM, decision trees, KNN, Naive Bayes, and evaluation metrics

1.

Evaluation Metrics

Classification and detection metrics — precision, recall, F1, IoU, NMS

2.

Bias-Variance Tradeoff

Understanding underfitting, overfitting, and the bias-variance decomposition

3.

Linear Regression

Closed-form and gradient descent solutions for linear regression

4.

Logistic Regression

Binary and multi-class classification using logistic regression with MLE derivation

5.

K-Nearest Neighbors

Non-parametric algorithm for classification and regression using distance metrics

6.

Naive Bayes

Probabilistic classifier based on Bayes' theorem with class-conditional independence

7.

Decision Tree

Recursive binary splitting for classification and regression with pruning

8.

Support Vector Machine

Margin-maximizing classifier with kernel trick for non-linear boundaries