Maths and ML foundations
- Python, NumPy and pandas for ML work
- Linear algebra: vectors, matrices, dot products, eigenvectors
- Calculus for ML: derivatives, gradients and gradient descent
- Probability, distributions and Bayes' theorem
- The ML workflow: train/validation/test splits, bias and variance
- Linear and logistic regression built from scratch, then with scikit-learn
- Evaluation metrics: RMSE, precision, recall, F1, ROC-AUC
Kochi practice: Container and shipping data for logistics analytics.