Skip to main content

Machine Learning

11 Modules ~40 hours Beginner → Advanced

Master Machine Learning end-to-end: math foundations, supervised/unsupervised algorithms, feature engineering, evaluation, neural networks, and ML in production. Builds toward our MLflow and llm-development tracks.

Course roadmap

#ModuleStatusTopics
0Setup & Math RefresherPlan readyPython, numpy, pandas, linear algebra essentials, calculus for grads
1ML FundamentalsPlan readySupervised vs unsupervised vs RL, train/val/test split, the bias-variance tradeoff
2Linear ModelsPlan readyLinear/logistic regression, regularization (L1/L2), gradient descent
3Tree-Based ModelsPlan readyDecision trees, random forests, gradient boosting (XGBoost, LightGBM)
4Unsupervised LearningPlan readyk-means, DBSCAN, hierarchical clustering, PCA, t-SNE, UMAP
5Feature EngineeringPlan readyEncoding, scaling, target encoding, feature selection, leakage detection
6Model EvaluationPlan readyCross-validation, metrics (precision, recall, AUC, MAE), error analysis
7Neural NetworksPlan readyPerceptron → MLP → backprop, PyTorch basics, GPU usage
8Deep Learning ArchitecturesPlan readyCNN, RNN/LSTM, Transformers introduction
9ML in ProductionPlan readyMLOps overview, model registry, monitoring, drift, fairness
10CapstonePlan readyBuild an end-to-end ML pipeline: data → model → registered → API

What's available now

Curriculum plan published. Content rolling out 2026 H2.

Related courses:

Last updated

2026-05 — Curriculum plan published.