This is a self study guide for learning full stack machine learning engineering, break down by topics and specializations. Python is the preferred framework as it covers end-to-end machine learning engineering. Highly recommended basic courses are marked with ⭐.
Basic computer science skill is required for machine learning engineering.
MIT: The Missing Sememster of Your CS Education ⭐
Corey Schafer Python Tutorials
edX MITX: Introduction to Computer Science and Programming Using Python ⭐
edX Harvard: CS50x: Introduction to Computer Science
Fundamentals of machine learning, including linear algebra, vector calculus, and statistics.
Mathematics for Machine Learning
The Elements of Statistical Learning
Pattern Recognition and Machine Learning: [Codes]
MIT 18.05: Introduction to Probability and Statistics ⭐
Stanford Stats216: Statiscal Learning ⭐
edX ColumbiaX: Machine Learning
Stanford CS229: Machine Learning
Stanford CS246: Mining Massive Data Sets
If a model was trained on a computer and no API is around to serve it, can it make an inference?
Machine Learning: The High Interest Credit Card of Technical Debt
How do Data Science Workers Collaborate? Roles, Workflows, and Tools
Software Engineering for Machine Learning: A Case Study
Toutiao (ByteDance/Tik-Tok) Recommendation System Design
Berkeley: Full Stack Deep Learning ⭐
Udemy: Deployment of Machine Learning Models ⭐
Udemy: The Complete Hands On Course To Master Apache Airflow
Machine learning is a sub field of Artificial Intelligence. These courses provides a much higher level understanding of the field of AI.
Artificial Intelligence: A Modern Approach
Berkeley CS188: Artificial Intelligence ⭐
edX ColumbiaX: Artificial Intelligence: [Reference Solutions]
Basic overview for deep learning.
Deeplearning.ai Deep Learning Specialization: [Reference Solutions] ⭐
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]
With languages models and sequential models, everyone can write like GPT-2.
Introduction to Natural Language Processing
Stanford CS224n: Natural Language Processing with Deep Learning: [Reference Solutions]
Berkeley CS182: Designing, Visualizing, and Understanding Deep Neural Networks: [Reference Solutions]
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
Stanford CS236: Deep Generative Models
Berkeley CS294-158: Deep Unsupervised Learning
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}
}