ML engineering education
A free hands-on course that teaches machine learning engineering end-to-end, from framing a problem to deploying a model with Docker, Kubernetes, and cloud services.
Same problem, same approach. Swapping one for another is a config change, not a rewrite.
Choose it for a similarly practical, production-focused ML engineering course with a permissive MIT license and code-first notebooks.
Learn how to develop, deploy and iterate on production-grade ML applications.
Solves the same problem with a different architecture or at a different layer. Expect to rewrite the integration.
Choose it when you want an interactive textbook combining math, CS, and ML foundations rather than a timed cohort course.
Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.
Choose it for a deeper, more academic survey of ML systems and edge deployment, rather than a 4-month hands-on cohort.
Machine Learning Systems: Foundations, Scaling, Agentic AI, and Physical AI (Vols I–IV) • Harvard CS249r | https://mlsysbook.ai
Choose it for a comprehensive open-book reference on ML engineering and training performance instead of a guided course.
Machine Learning Engineering Open Book
An earlier or more limited way to do the job. Still the right call when you need something small, proven, or CPU-only.
Choose it when you prefer a deep-learning-first book/course with fastai/PyTorch instead of broad ML engineering/deployment.
The fastai book, published as Jupyter Notebooks
Choose it for an up-to-date, notebook-driven ML/DL modeling course with scikit-learn/Keras/TensorFlow, but no MLOps/deployment coverage.
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
Choose it for a structured introductory ML course with theory, assignments, and community, if you don't need production/deployment content.
Open Machine Learning Course
Choose it for a hands-on PyTorch deep-learning course instead of a broad ML engineering pipeline.
Materials for the Learn PyTorch for Deep Learning: Zero to Mastery course.
Choose it for a university-style ML course with labs and assignments, not MLOps/deployment.
Open Machine Learning course
Choose it for an introductory university ML course (in Persian) focusing on fundamentals, not production systems.
Machine Learning Course, Sharif University of Technology
Choose it for a beginner data-science/ML course, but note it is older and lacks MLOps depth.
All course materials for the Zero to Mastery Machine Learning and Data Science course.
Choose it for an older, unmaintained free Python ML course if you don't need recent updates.
:speech_balloon: Machine Learning Course with Python:
It is the deprecated previous edition of handson-ml, useful only for the older scikit-learn/TF content.
⛔️ DEPRECATED – See https://github.com/ageron/handson-ml3 or handson-mlp instead.
It is an archived, TensorFlow-specific old Stanford tutorial set, useful only for legacy TF learning.
This repository contains code examples for the Stanford's course: TensorFlow for Deep Learning Research.
Choose it to specialize in LLM workflows and roadmaps rather than broad ML engineering; it is narrower in scope.
Course to get into Large Language Models (LLMs) with roadmaps and Colab notebooks.
These projects were analysed and named machine-learning-zoomcamp among their alternatives. The relationship is not symmetric — how machine-learning-zoomcamp rates them is a separate judgement, made when machine-learning-zoomcamp is analysed in its own right.
calls machine-learning-zoomcamp “An actively maintained, free cohort-based ML engineering course that can replace the Zero to Mastery materials.”
All course materials for the Zero to Mastery Machine Learning and Data Science course.
calls machine-learning-zoomcamp “Choose for a project-based ML engineering bootcamp with hands-on homework.”
Interactive deep learning book with multi-framework code, math, and discussions. Adopted at 500 universities from 70 countries including Stanford, MIT, Harvard, and Cambridge.
calls machine-learning-zoomcamp “Structured ML engineering course with assignments; choose for instructor-led format over self-guided notebooks.”
Data science Python notebooks: Deep learning (TensorFlow, Theano, Caffe, Keras), scikit-learn, Kaggle, big data (Spark, Hadoop MapReduce, HDFS), matplotlib, pandas, NumPy, SciPy, Python essentials, AWS, and various command lines.
calls machine-learning-zoomcamp “When you want a free, structured ML engineering bootcamp.”
A series of Jupyter notebooks that walk you through the fundamentals of Machine Learning and Deep Learning in Python using Scikit-Learn, Keras and TensorFlow 2.
calls machine-learning-zoomcamp “Choose if you want a structured ML engineering course with notebooks over platform-specific examples.”
Example 📓 Jupyter notebooks that demonstrate how to build, train, and deploy machine learning models using 🧠 Amazon SageMaker.
calls machine-learning-zoomcamp “when you want an engineering-focused ML curriculum (deployment, MLOps) rather than theory-heavy classical ML.”
Open Machine Learning Course
calls machine-learning-zoomcamp “Use it when you prefer a structured, free ML-engineering bootcamp with a schedule instead of a self-study compendium.”
Become a cracked AI/ML researcher/engineer with this unconventional textbook covering maths, computing, and ML with intuition.
calls machine-learning-zoomcamp “Choose if you want an ML engineering/MLOps curriculum with deployment projects rather than a theory-and-notebooks course.”
Machine Learning Course, Sharif University of Technology