Big Data & ML·Course
Big Data & Machine Learning
Big data: Hadoop, Spark, streaming, feature engineering, GNN, MLOps, and responsible AI
Part of the Mathematics track — finish it for a verifiable diploma →
§ 01 — Orientation
New here?
What you'll be able to do, who this is for, how long it takes, and where to begin.
By the end, you will be able to
- 01Design a data pipeline that scales.
- 02Engineer features that make models work.
- 03Choose the right advanced architecture.
- 04Ship and monitor models with MLOps.
- 05Weigh the ethics of an ML system.
Who this is for
How long it takes
- Quick orientationSkim the opening module and the cheatsheet to get the shape of it.~2 h
- Full read-throughRead every article once, in order.~2 h
- Mastery pathRead, take the quizzes, and space out your reviews.~2 weeks
- APA
Stoa. (2026). Big Data & Machine Learning [Online course]. Stoa. https://stoa.school/course/big-data-dl
- MLA
Stoa. “Big Data & Machine Learning.” Stoa, 2026, https://stoa.school/course/big-data-dl.
- Chicago
Stoa. “Big Data & Machine Learning.” Stoa. Accessed September 1, 2026. https://stoa.school/course/big-data-dl.
§ 02 — Curriculum
5 modules.
Each module is a small unit. Most read in sequence — but a determined reader can begin anywhere.
- M IModern Machine Learning MethodsGradient boosting, ensemble methods, reinforcement learning3 articles
18 minBegin → - M IIMathematical Foundations of Deep LearningApproximation theory, backpropagation, transformers3 articles
18 minBegin → - M IIIHigh-Dimensional StatisticsCurse of dimensionality, sparsity, LASSO, Ridge, PCA3 articles
18 minBegin → - M IVConvex Optimization for MLProximal gradient methods, Adam, SGD, convergence theory3 articles
18 minBegin → - M VAlgorithms for Big DataRandomized linear algebra, hashing, streaming algorithms3 articles
18 minBegin →
§ 03 — Learning outcomes
4 outcomes.
Design and use big data processing systems (Hadoop, Spark, Kafka)
Develop features for ML models and process structured and unstructured data
Apply graph neural networks and specialized deep learning architectures
Deploy ML systems in production and ensure fairness and explainability
§ 04 — Practices