A series of Jupyter notebooks teaches machine learning and deep learning in Python with Scikit-Learn, Keras, and TensorFlow.
Open source
24 alternativesMachine Learning Visualized
Jupyter notebooks implement and derive machine learning algorithms from first principles using NumPy.
About Machine Learning Visualized
Machine Learning Visualized is an open-source Jupyter Book that implements and mathematically derives machine learning algorithms from first principles, using NumPy. Each notebook produces a visualization of the algorithm during training, showing it converge toward its optimal weights. The site also includes interactive notebooks built with Marimo that show how weights affect loss functions.
This repository holds only the configuration and build code for the book. The notebooks themselves live in separate repositories, one per algorithm, and a shell script downloads them before the book is built. The listed algorithms are neural networks, autoencoders, logistic regression, perceptrons, principal component analysis, k-means, and gradient descent.
Key features
- Jupyter Notebooks that implement and derive ML algorithms from first principles
- Marimo interactive notebooks showing how weights affect loss functions
- Visualizations of each algorithm's training phase converging to optimal weights
- Shell script that downloads notebooks from separate per-algorithm repositories
- Local book build through the jupyter-book CLI, Docker Compose, or Docker
- Instructions for building an EPUB version of the combined notebooks
Best for: Learners who want to understand how machine learning algorithms work by following their derivations and watching them train, using Python and NumPy.
Good for
- Released under the MIT license
- Each algorithm is both implemented and mathematically derived
- Training is shown as a visualization rather than only as final results
Watch out for
- The notebooks are not stored in this repository and must be downloaded before the book can be built
- Building the book locally requires installing jupyter-book or Docker
- The EPUB build instructions list MacTeX as a macOS installation step
Machine Learning Visualized at a glance
- Category
- Education & Learning › Learn to Code
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
Machine Learning Visualized alternatives
Tools and sites you could use instead, ranked by how closely they match.
This tutorial walks through training and deploying a machine learning REST API that predicts cryptocurrency prices in ten steps.
Open source
24 alternatives
A Python learning playground and cheat sheet organizes example scripts by topic, with explanations for the code.
Open source
24 alternatives
Data Science IPython Notebooks collects notebooks about data science, including TensorFlow deep learning.
This repository walks through implementing a ChatGPT like language model in PyTorch, step by step.
This open book collects methods, tools, and instructions for training, fine-tuning, and running machine learning models.
Popular in Learn to Code
Well-known listings from the same topic.
Codelabscodelabs.developers.google.comScratchscratch.mit.eduTelegram Bot APIcore.telegram.org/botsStudent Developer Packeducation.github.com/packHacksplaininghacksplaining.comQB64SourceCodeqb64tutorial.com
Machine Learning Visualized FAQ
Where are the notebooks stored?
They are not in this repository. Each algorithm has its own repository, and a shell script named download_notebooks.sh downloads the relevant notebooks before the book is built.
Which algorithms are covered?
The repository links to notebooks for neural networks, autoencoders, logistic regression, perceptrons, principal component analysis, k-means, and gradient descent.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.