The High Cost of Maintaining Machine Learning Systems

Overfitting vs. Underfitting: A Conceptual Explanation

11 Clever Methods of Overfitting and How to Avoid Them

"So, you want to build an ethical algorithm?" An interactive tool to prompt discussions 

What is the difference between Data Analytics, Data Analysis, Data Mining, Data Science, Machine Learning, and Big Data?

"MLOps" overlaps with Data Eng, and there's 

"Advice on building a machine learning career and reading research papers by Prof. Andrew Ng"

Python Data Science Handbook, as Jupyter Notebooks

Prof. Pedro Domingos's introductory video series. 

Advanced Statistical Computing (Vanderbilt BIOS8366). Interactive.

UC Berkeley's Data 8: The Foundations of Data Science course and the textbook 

An epic Quora thread: How can I become a data scientist?

"Implemented with NumPy/MXNet, PyTorch, and

"The entire book is drafted in Jupyter notebooks, seamlessly integrating exposition figures, math, and interactive examples with self-contained code."

"You can modify the code and tune hyperparameters to get instant feedback to accumulate practical experiences in deep

Quora: "What are the best ways to pick up Deep Learning skills as an engineer?" — answered by Greg Brockman (Co-Founder &amp; CTO at OpenAI, previously CTO at Stripe)

Creative Applications of Deep Learning with Tensorflow

Distill.pub publishes explorable explanations that are really great.

"Feature Visualization: How neural networks build up their understanding of images"

, "A refreshing functional take on deep learning, compatible with your favorite libraries"

 by Jeremy Howard and Sylvain Gugger - "These notebooks cover an introduction to deep learning, 

JAX - official quickstart Colab Notebooks to get to know JAX

markusschanta/awesome-jupyter, "Hosted Notebook Solutions"

ml-tooling/best-of-jupyter, "Notebook Environments"

Study tips for Prof. Andrew Ng's course, by Ray Li

 - "This cheatsheet is a 10-page reference in probability that covers a semester's worth of introductory probability. The cheatsheet is based off of Harvard's introductory probability course, Stat 110. It is co-authored by former Stat 110 Teaching Fellow William Chen and Stat 110 Professor Joe Blitzstein." 

Probabilities and statistics refresher cheat sheet from 

Machine Learning tips and tricks cheat sheet

Accessible data science book, no coding experience required:

Data Science Workflow: Overview and Challenges (read the article 

Then, over time, you can listen to the entire podcast series (start from the

For Machine-Learning libraries that might not be on PyPI, GitHub, etc., there's

Jupyter Notebook. (Formerly known as IPython Notebook.)

Video series from Data School, about Pandas. "Reference guide to 30 common pandas tasks (plus 6 hours of supporting video)."

Here are some docs I found especially helpful as I continued

Group By (split, apply, and combine DataFrames)

: A Pandas-like interface, but for larger-than-memory data and "under the hood" parallelism.

spaCy: Industrial-strength NLP - "spaCy is a library for advanced Natural Language Processing in Python and Cython."

Advanced NLP with spaCy: A free online course

spaCy projects - "End-to-end NLP workflows from prototype to production"

"Learning How to Learn" by Barbara Oakley by Barbara Oakley, a free video course on Coursera.

Example Machine Learning notebook, exercise, and guide by Dr. Randal S. Olson. Mentioned in Notebooks section as well, but it has a similar goal to this guide (introduce you, and show you where to go next). Rich "Further Reading" section.

Courses by cloud vendors. These are usually high quality content but steer you heavily to use vendor-specific tools/services. I encourage you to "make the most" of the resources that they make freely available. To avoid getting locked into vendor specifics, just make sure you're learning from other resources as

Machine Learning Crash Course from Google with TensorFlow APIs.

Amazon AWS Amazon have open up their internal training to the public and also offer certification.

Machine Learning for Developers is good for people who are more familiar with Java or Scala than Python.

rasbt/python-machine-learning-book-3rd-edition aka 

Machine Learning for Software Engineers, by Nam Vu. In their words, it's a "top-down and results-first approach designed for software engineers." Definitely bookmark and use it, as well - it can answer lots of questions and connect you with great resources.

More ways to "Dive into Machine Learning"

, a 5-project series - paid but the first project is free.

Aside: Bayesian Statistics and Machine Learning

Easily try out deep learning models from your

The demos link to papers/code on GitHub, if you want to dig in and see how something

Easier sharing of deep learning models and demos

Repository of DIVE INTO MACHINE LEARNING Resources in April 2025

Select category under dive-into-machine-learning projects and apps that you are looking to build in April 2025

Last Updated: 13 April 2025

Repository of dive into machine learning Resources

Subscribe to our Newsletter

Company

Follow Us

Subscribe to our Newsletter