M42 — Orion Nebula

Data Science Learning Resources

Data Science is a very interesting area to learn about. To help you with that I collected here some resources which are mostly free, but of high quality.

Absolute Beginner

If your are an absolute beginner and want to know more about data science I recommend the following courses:

• https://open.hpi.de/courses/data-engineering2020 (german)
• https://open.hpi.de/courses/kieinstieg2020 (german)
• https://developers.google.com/machine-learning/foundational-courses
• https://developers.google.com/machine-learning/glossary

Data Science and Machine Learning

For data science and machine learning in general I like the following books and lectures the most:

Beginners

Scipy Lecture Notes

• https://scipy-lectures.org/

Brownlee: Machine Learning Mastery

• https://machinelearningmastery.com/start-here

Segaran 2007: Programming Collective Intelligence

• https://www.oreilly.com/library/view/programming-collective-intelligence/9780596529321/

I want to note here that the term “collective intelligence” is much better than “artificial intelligence”. It makes clear that data scientists are not building some homunculus. Instead data scientists and machine learning engineers are extracting patterns from huge amounts of data and use these patterns to classify, predict or generate new data. Unfortunately the term “collective intelligence” — as suggested by the Segaran— did not become very popular, but I think it should be.

Grus 2019: Data Science from scratch

• https://covid19.uthm.edu.my/wp-content/uploads/2020/04/Data-Science-from-Scratch-First-Principles-with-Python-by-Joel-Grus-z-lib.org_.epub_.pdf
• https://github.com/joelgrus/data-science-from-scratch

VanderPlas 2023: Python Data Science Handbook

• https://jakevdp.github.io/PythonDataScienceHandbook/

Advanced

Bishop 2006: Pattern Recognition and Machine Learning

• https://www.microsoft.com/en-us/research/uploads/prod/2006/01/Bishop-Pattern-Recognition-and-Machine-Learning-2006.pdf
• https://www.microsoft.com/en-us/research/people/cmbishop/prml-book/

Hastie 2017: The Elements of Statistical Learning

• https://hastie.su.domains/ElemStatLearn/

Geron 2022: Hands-On Machine Learning with Scikit-Learn & TensorFlow

• https://www.oreilly.com/library/view/hands-on-machine-learning/9781098125967/
• https://github.com/ageron/handson-ml3

James 2023: An Introduction to Statistical Learning (with Applications in Python)

• https://www.statlearning.com/

Deep Learning

If you want to know more about deep learning specifically you will find the following books and courses helpful:

GoodFellow et.al. 2016: Deep Learning

• https://www.deeplearningbook.org/
• https://github.com/janishar/mit-deep-learning-book-pdf

Howard, Gugger: Deep Learning for Coders with Fastai and PyTorch: AI Applications Without a PhD

• https://github.com/fastai/fastbook

Howard et.al: Practical Deep Learning for Coders

• https://course.fast.ai/

Zhang et.al. : Dive into Deep Learning

• https://d2l.ai/
• https://www.heise.de/hintergrund/Dive-Into-Deep-Learning-Ein-interaktives-Buch-fuer-DL-7337410.html

UPDATE:

This book was published just recently and is endorsed by the the “Godfathers of Deep Learning” Hinton, LeCun and Bengio:

Bishop et. al. 2023: Deep Learning: Foundations and Concepts

• https://www.bishopbook.com/

Recommendation

If I would have to choose just one resource from above it would be

Geron 2022: Hands-On Machine Learning with Scikit-Learn & TensorFlow

• https://www.oreilly.com/library/view/hands-on-machine-learning/9781098125967/
• https://github.com/ageron/handson-ml3

It has a very good mixture of theory and practice. It also includes Deep Learning, Transformers, GANS and Reinforcement Learning. It is up-to-date. It also has historical information and points to very interesting resources itself. It has everything, except for a low price.