This is curated list of publicly accessible machine learning coureses from top universities such as Berkeley, Harvard, Stanford, and MIT. It also includes machine learning project case studies from large and experienced companies. THe list is broken down by topics and areas of specializations. Python is the preferred language of choice as it covers end-to-end machine learning engineering.
Special thanks to the schools to make their course videos and assignments publicly available.
Foundational computer science, Python, and SQL skills for machine learning engineering.
Design Patterns: Elements of Reusable Object-Oriented Software 1st Edition
MIT: The Missing Sememster of Your CS Education ⭐
edX MITX: Introduction to Computer Science and Programming Using Python ⭐
edX Harvard: CS50x: Introduction to Computer Science
U Waterloo: CS794: Optimization for Data Science
Berkeley CS 170: Efficient Algorithms and Intractable Problems
Berkeley CS 294-165: Sketching Algorithms
Linear algebra and statistics
NIST Engineering Statistics Handbook
MIT 18.05: Introduction to Probability and Statistics ⭐
Stanford Stats216: Statiscal Learning ⭐
A Students Guide to Bayesian Statistics
Introduction to Linear Algebra for Applied Machine Learning with Python
Artificial Intelligence is the superset of Machine Learning. These courses provides a much higher level understanding of the field of AI, including searching, planning, logic, constrain optimization, and machine learning.
Artificial Intelligence: A Modern Approach
Berkeley CS188: Artificial Intelligence ⭐
edX ColumbiaX: Artificial Intelligence: [Reference Solutions]
Machine learning.
Mathematics for Machine Learning
The Elements of Statistical Learning
Pattern Recognition and Machine Learning: [Codes]
Cross-Industry Process for Data Mining methodology
Stanford CS229: Machine Learning 📺
Columbia COMS W4995: Applied Machine Learning 📺
edX ColumbiaX: Machine Learning
Berkeley CS294: Fairness in Machine Learning
Google: Machine Learning Crash Course
Google: Applied Machine Learning Intensive
Cornell Tech CS5785: Applied Machine Learning 📺
Probabilistic Machine Learning (Summer 2020) 📺
AutoML - Automated Machine Learning
These courses helps you bridge the gap from training machine learning models to deploy AI systems in the real world.
Machine Learning System Design
Microsoft Commercial Software Engineering ML Fundamentals
Feature Engineering and Selection: A Practical Approach for Predictive Models
Continuous Delivery for Machine Learning
Berkeley: Full Stack Deep Learning ⭐
CMU: Machine Learning in Production github
Andrew Ng: Bridging AI's Proof-of-Concept to Production Gap
Facebook Field Guide to Machine Learning
Udemy: Deployment of Machine Learning Models ⭐
Udemy: The Complete Hands On Course To Master Apache Airflow
Basic overview for deep learning.
The Matrix Calculus You Need For Deep Learning
Berkeley CS 182: Designing, Visualizing and Understanding Deep Neural Networks
Stanford CS 25: Transformers 📺
Deeplearning.ai Deep Learning Specialization: [Reference Solutions] ⭐
Recommendation system is used when users do not know what they want and cannot use keywords to describe needs.
Speech and Language Processing
Dive into Deep Learning: Chapter 16 Recommender Systems
Stanford CS246: Mining Massive Data Sets
Search and Ranking is used when users have specific needs and can use keywords to describe their needs.
Introduction to Information Retrieval
Stanford CS276: Information Retrieval and Web Search
University of Freiburg: Information Retrieval 📺
With languages models and sequential models, everyone can write like GPT-3.
Introduction to Natural Language Processing
Speech and Language Processing
Stanford CS224n: Natural Language Processing with Deep Learning: [Reference Solutions] ⭐
Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks: 📺 [Reference Solutions]
[NYU: DS-GA 1011 Natural Language Processing with Representation Learnin] (https://www.youtube.com/playlist?list=PLdH9u0f1XKW_s-c8EcgJpn_HJz5Jj1IRf)
Deeplearning.ai Natural Language Processing Specialization [Reference Solutions]
Neural nets cannot solve all vision problems, yet.
Stanford CS231n: Convolutional Neural Networks for Visual Recognition: [Assignment 2 Solution, Assignment 3 Solution] ⭐
Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks: 📺 [[Reference Solutions]
Stanford CS236: Deep Generative Models
Berkeley CS294-158: Deep Unsupervised Learning
Coursera: Reinforcement Learning Specialization <= Recommended by Richard Sutton, the author of the de facto textbook on RL. ⭐
Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks: 📺 [Reference Solutions]
Stanford CS234: Reinforcement Learning
Berkeley CS285: Deep Reinforcement Learning ⭐
CS 330: Deep Multi-Task and Meta Learning: Videos
Berekley: Deep Reinforcement Learning Bootcamp
IDS at Stanford RL forum Video 1 Video 2 Slides
Quaternions, quaternions everywhere. And gradients.
All books, blogs, and courses are owned by their respective authors.
You can use my compilation and my reference solutions under the open CC BY-SA 3.0 license and cite it as:
@misc{leehanchung,
author = {Lee, Hanchung},
title = {Full Stack Machine Learning Engineering Courses},
year = {2020},
howpublished = {Github Repo},
url = {https://github.com/full_stack_machine_learning_engineering_courses}
}