This curated AI and machine learning guide organizes over 228 learning resources across 30 sections.
ML Visualized
Machine Learning Visualized organizes its material as a collection of visual learning resources in a repository.
About ML Visualized
Machine Learning Visualized is a collection of Python Jupyter Notebooks that implement machine learning algorithms from first principles with mathematical derivations. Each notebook visualizes an algorithm during training as it converges to optimal weights.
The collection covers optimization, clustering and reduction, linear models, and neural networks, with related lecture notes. Notebooks can be downloaded as .ipynb files to run locally or on cloud services such as Google Colab.
Key features
- Jupyter Notebooks implementing machine learning algorithms from first principles
- Visualizations of algorithm training converging to optimal weights
- Downloadable .ipynb files to run locally or on Google Colab
- Gradient descent, K-Means, PCA, perceptron, and logistic regression notebooks
- Neural network, backpropagation, and autoencoder visualization notebooks
- Terraform scripts to spin up AWS SageMaker notebooks
Best for: Students learning machine learning who want visual, code-based explanations of core algorithms.
Good for
- Implements algorithms from first principles with mathematical derivations
- Shows training progress through visualizations ending at optimal weights
- Notebooks can be downloaded as .ipynb files for local or cloud execution
ML Visualized at a glance
- Website
- ml-visualized.com
- Category
- Education & Learning › Learn to Code
- Type
- Website
- Pricing
- Not confirmed. Check the site
- Platforms
- Web
- Open source
- Not stated
- Language
- English
- Last checked
- Oct 5, 2026 · Online when checked
- Listed
- Oct 5, 2026
ML Visualized alternatives
Tools and sites you could use instead, ranked by how closely they match.
A curated repository helps readers discover machine learning and AI courses published on YouTube.
Open source
24 alternativesVirgilio organizes data science e-learning resources in a structured project overview.
This Awesome DataScience repository collects learning material and resources about data science.
Open source
24 alternativesStrataScratch offers over 1,000 data science interview questions across SQL, Python, statistics, machine learning, and data projects.
Machine Learning Systems is a two-volume textbook about how machine learning systems are built, covering the engineering behind AI.
Free
24 alternativesPopular 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
ML Visualized FAQ
How can I run the notebooks myself?
Click the download icon at the top right of any page, select the .ipynb option, then open and run the code blocks locally or on the cloud, like Google Colab.
How can I contribute a notebook?
Upload your notebook to your own GitHub repository and make a pull request following the reference commit; after approval the build downloads the .ipynb file and updates the site.
Is there an option for advanced users to run notebooks on AWS?
Yes, the site provides Terraform scripts to spin up AWS SageMaker notebooks.
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.