One question that has frequently come my way lately is, “How can one embark on their AI journey?” A few years ago, answering this question would have been straightforward. However, with the recent rapid advancements spanning various AI domains, particularly in NLP and computer vision, and the abundance of online resources available today, outlining a comprehensive roadmap has become a nuanced task.
After careful consideration, I’ve crafted a straightforward yet potent A-to-Z curriculum. This guide is designed to be inclusive, catering to individuals with diverse backgrounds — whether they are newcomers to the field or professionals seeking a career shift. These resources can also be beneficial for advanced ML engineers who want to refresh some concepts.
The structure of this guide is deliberate and includes a personally curated list of online courses. Since this repository is beginner-friendly, I only included important structured courses in the main curriculum because they are organized and easier to follow. Additional resources will be added in separate sections. Take the main curriculum courses in order for better understanding.
This repository is open to all kinds of contributions related to the machine learning journey. However, there are some considerations:
- Since the purpose here is to make a straightforward guide, additional courses, and books won't be added to the main curriculum. Rather they will be added in a separate section.
- If a course meets standards, it will become a part of the main curriculum.
- Resources can be free and paid.
- Make sure to follow the format for resources i.e. name, links, and institute/person.
- Resources can include YouTube channels, papers, blog posts, online courses, and book recommendations.
- Fork this repository
- Add your contribution (do not modify the original list)
- Create Pull Request
- There aren't many resources related to MLOps included in this repository since I am planning to create a separate repository for that.
- Practical resources and projects coming soon.
- AI learning is a journey, not a sprint; success requires resisting impatience, embracing challenges, and fostering a deep understanding of AI principles despite the temptation for quick results.
- Broaden your machine learning understanding through diverse resources like instructors, courses, books, research papers, and blogs for a well-rounded grasp of artificial intelligence.
- Focus on mastering one concept at a time for a solid foundation and effective learning.
- Theory is vital, but true understanding comes from hands-on implementation; actively engage with knowledge, invest time in real-world problem-solving, and trust the process for profound insights.
- AI success requires technical skills and more—embrace GitHub, Docker, diverse programming languages, paper-reading, cloud computing, project management, and strong writing/documentation for adaptability in the evolving industry.
Mathematics for Machine Learning and Data Science Specialization by Coursera
CS50’s Introduction to Computer Science
Complete Python Developer: Zero to Mastery (You can often find it on Udemy on sale.)
Machine Learning Specialization by DeepLearningAI x Stanford
Introduction to Machine Learning by Sebastian Raschka
CS231N: Convolutional Neural Networks for Visual Recognition by Stanford
Introduction to Deep Learning by Sebastian Raschka
CS224N: Natural Language Processing with Deep Learning by Stanford
Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow, 3rd Edition by Aurélien Géron
Mathematics for Machine Learning
Statistics and Probability by Khan Academy
Essense of Linear Algebra by 3Blue1Brown
Neural Networks: Zero to Hero by Andrej Karpathy
Deep Learning Specialization by DeepLearningAI
MIT 6.S191: Introduction to Deep Learning
Deep Learning Fundamentals — Learning Deep Learning With a Modern Open Source Stack
Practical Deep Learning for Coders
Introduction to Reinforcement Learning by Deepmind
CS50’s Introduction to Artificial Intelligence with Python
A detailed list of courses by Aman Chadha
Machine Learning Crash Course by Google
Applied Machine Learning by Cornell University
Deep learning by Ian Goodfellow and Yoshua Bengio and Aaron Courville
The Hundred-Page Machine Learning Book by Andriy Burkov
Aleksa Gordić - The AI Epiphany
NumPy tutorial by Stanford CS231N
Visit my website for some project ideas.
Coming soon.
"Yes you should understand backprop" by Andrej Karpathy
"A Recipe for Training Neural Networks" by Andrej Karpathy
"The Unreasonable Effectiveness of Recurrent Neural Networks" by Andrej Karpathy
"Understanding LSTM Networks" by Chris Olah
"The Illustrated Transformer" by Jay Alammar
"Illustrating Reinforcement Learning from Human Feedback (RLHF)" by HuggingFace
"RLHF: Reinforcement Learning from Human Feedback" by Chip Huyen