AI Learning Resources
Some recommended AI/ML learning resources
Overview
Choosing an AI/ML learning resource is primarliy a matter of personal preference. In general, I recommend that you refer to more than one resource (other than documentation) when learning AI.
If you have an .edu email account you can get free access to oreilly.com which has some good books for beginners as well as advanced books on various AI/ML topics. The article Creating an Account describes what to do if your school is not in the list.
Beginner Learning Path
This article is mainly a collection of resources, but here is one possible learning path for beginners:
- QuickStart for Beginners
- Prerequisite Textbooks
- Linux Resources
- Books for Beginners (choose one or two)
- Books for Developers
- Graduate Textbooks
QuickStart for Beginners
Here are some quickstart resources that can help an experienced software engineer learning AI:
- Machine Learning Guide
- Machine Learning Glossary
- Data Science Cheatsheet
- Machine Learning Mastery — Getting Started Guides
- A Beginner’s Guide to End to End Machine Learning
- OSSU Computer Science
- OSSU Data Science
Be sure to see Prerequisite Textbooks below.
Linux Resources
Even if you are just learning AI/ML, you should be learning and using Linux.
Articles for Beginners
Here are some articles for beginners that introduce the core models and concepts:
- Practical Guide to Linear Regression
- Regression for Classification
- End-to-End Machine Learning Workflow (Part 1)
- End-to-End Machine Learning Workflow (Part 2)
- 6 Predictive Models Every Beginner Data Scientist Should Master
- 10 Simple Things to Try Before Neural Networks
- Deep Learning with Python: Neural Networks (complete tutorial)
Articles for Developers
Here are some articles and other resources for developers:
- Machine Learning Mastery — Getting Started Guides
- Deep Learning Performance Cheat Sheet
- Collection of Cheatsheets
- How to Select an ML Model?
- Brief Guide for Machine Learning Model Selection
- 63 Machine Learning Algorithms (11 Categories)
- The Algorithms — Python
Books for Beginners
Here are some books on oreilly.com that may be helpful:
- Hands-On Artificial Intelligence for Beginners
- Python Artificial Intelligence Projects for Beginners
- 6 Free Data Science Books for Complete Beginners
Books for Developers
I have found some of the books in the Pragmatic Bookshelf series (available on oreilly.com) to be helpful if you already have extensive software engineering experience:
- A Common-Sense Guide to Data Structures and Algorithms
- Programming Machine Learning
- Hands-On Machine Learning with Scikit-Learn, Keras, and TensorFlow
- Practical Machine Learning for Computer Vision
One or two of the following books on oreilly.com should be helpful:
- Artificial Intelligence with Python
- Artificial Intelligence by Example
- Python Machine Learning
- Python Machine Learning By Example
Prerequisite Textbooks
Here are some textbooks that cover the core mathematical concepts but should not be the first time you have seen the material:
K. Rosen, Discrete Mathematics and Its Applications, 8th ed., McGraw Hill, ISBN: 978–1–259–67651–2, 2019.
J. Fanchi, Math Refresher for Scientists and Engineers, 3rd ed., Wiley, ISBN: 0–471–75715–2, 2006.
M. P. Deisenroth, A. A. Faisal, and C. S. Ong, Mathematics for Machine Learning, Cambridge, UK: Cambridge University Press, ISBN: 978–1–108–47004–9, 2020.
These textbooks cover topics that are usually required for a degree in computer science:
R. V. Hogg, J. W. McKean, and A. T. Craig, Introduction to Mathematical Statistics, Pearson, ISBN 0134686993, 2019.
C. Hamacher, Z. Vranesic, S. Zaky, and N. Manjikian, Computer Organization and Embedded Systems, 6th ed., McGraw Hill, ISBN: 978–0–07–338065–0, 2012.
A. S. Tanenbaum and D. J. Wetherall, Computer Networks, 5th ed., Pearson, ISBN: 0–13–212695–8, 2011.
R. H. Arpaci-Dusseau and A. C. Arpaci-Dusseau, Operating Systems: Three Easy Pieces, 2018, v. 1.01, Available online: pages.cs.wisc.edu/~remzi/OSTEP
Here are some landmark textbooks and references on software engineering best practices that are highly recommended:
S. McConnell, Code Complete, 2nd ed., Microsoft Press, ISBN: 0–7356–1967–0, 2004.
M. Howard and D. LeBlanc, Writing Secure Code, 2nd ed., Microsoft Press Press, ISBN: 0735617228, 2003.
P. Bourque and R. E. Fairley, Guide to the Software Engineering Body of Knowledge, v. 3, IEEE, 2014.
Graduate Textbooks
Here are the graduate textbooks on AI that seem to be the standard learning resources for AI/ML (see Prerequisite Textbooks):
E. Alpaydin, Introduction to Machine Learning, 4th ed., MIT Press, ISBN: 9780262358064, 2020.
S. Russell and P. Norvig, Artificial Intelligence: A Modern Approach, 4th ed. Upper Saddle River, NJ: Prentice Hall, ISBN: 0–13–461099–7, 2021.
W. McKinney, Python for Data Analysis: Data Wrangling with Pandas, NumPy, and IPython, 2nd ed., O’Reilly Media, ISBN: 978–1491957660, 2017.
S. Raschka. and V. Mirjalili, Python Machine Learning, 2nd ed. Packt, ISBN: 978–1787125933, 2017.
S. Bird, E. Klein, and E. Loper, Natural Language Processing with Python — Analyzing Text with the Natural Language Toolkit.
D. Jurafsky and J. H. Martin, 2nd edition. Speech and Language Processing. Prentice Hall, ISBN: 978–0131873216, 2008.
B. Siciliano, L. Sciavicco, L. Villani, and G. Oriolo, Robotics: Modeling, Planning and Control, London: Springer, ISBN: 978–1–84628–641–4, 2010.
J. Zobel, Writing for Computer Science, 3rd ed., London: Springer, ISBN: 978–1–4471–6638–2, 2014.
Resources on Advanced Concepts
Here are some resources on various AI topics that I have found useful:
- Machine learning system design patterns
- Serving ML Models in Production: Common Patterns
- Design Patterns for Machine Learning Pipelines
K. NG, A. Padmanabhan, and M. R. Cole, Mobile Artificial Intelligence Projects, Birmingham, U.K.: Packt Pub. Ltd., 2019.
F. X. Govers, Artificial Intelligence for Robotics, Birmingham, U.K.: Packt Pub. Ltd., 2018.
V. Lakshmanan, S. Robinson, M. Munn, Machine Learning Design Patterns, Sebastopol, CA: O’Reilly Media, Inc., 2021.
P. Palanisamy, Hands-On Intelligent Agents with OpenAI Gym, Birmingham, U.K.: Packt Pub. Ltd., 2018.
H. Lin and B. Biggio, “Adversarial Machine Learning: Attacks From Laboratories to the Real World,” IEEE Computer, May 2021.
Code Repos
aima-python: Python code for Artificial Intelligence: A Modern Approach.
rasbt/python-machine-learning-book-3rd-edition
AI News Feeds
Here are some RSS feeds that I have found helpful using the NetNewsWire iOS app:
Here are some RSS feeds on Medium that I have found useful:
Enjoy!
