What is machine-learning-tutorials?

ujjwalkarn/machine-learning-tutorials — explained in plain English

Analysis updated 2026-06-24

★ 17,806Audience · dataComplexity · 1/5Setup · easy

Mindmap

mindmap
  root((ML Tutorials))
    What it does
      Curated learning list
      Structured by topic
      Beginner to advanced
    Topics covered
      Classical ML
      Deep learning
      NLP and vision
      Reinforcement learning
    Use cases
      Self-study ML
      Interview preparation
      Topic deep dives
    Audience
      ML beginners
      Data scientists
    Format
      Tutorials
      University courses
      Articles

mindmap root((ML Tutorials)) What it does Curated learning list Structured by topic Beginner to advanced Topics covered Classical ML Deep learning NLP and vision Reinforcement learning Use cases Self-study ML Interview preparation Topic deep dives Audience ML beginners Data scientists Format Tutorials University courses Articles

Click or tap to explore — scroll the page freely

What do people build with it?

USE CASE 1

Find curated courses and tutorials to learn machine learning from scratch without sifting through search results.

USE CASE 2

Prepare for data science interviews with a structured refresher on classical ML techniques like random forests and SVMs.

USE CASE 3

Discover tutorials on specific deep learning topics such as CNNs, RNNs, or reinforcement learning.

What is it built with?

Python

How does it compare?

	ujjwalkarn/machine-learning-tutorials	dexteryy/spellbook-of-modern-webdev	pinojs/pino
Stars	17,806	17,808	17,803
Language	—	—	JavaScript
Setup difficulty	easy	easy	easy
Complexity	1/5	1/5	2/5
Audience	data	developer	developer

Figures from each repo's GitHub metadata at analysis time.

How do you get it running?

Difficulty · easy Time to first run · 5min

License terms not described in the guide.

So what is it?

This repository is a curated reference list of tutorials, articles, courses, and other learning resources for machine learning and deep learning. It is not a library or tool, it is a structured collection of links organised by topic to help people learn or deepen their understanding of AI concepts. Machine learning is a field of computer science where programs learn patterns from data rather than being explicitly programmed with rules. Deep learning is a subset of machine learning that uses multi-layered neural networks (software systems loosely modelled on how brains work) to handle tasks like image recognition, language understanding, and more. The list is organised into clearly labelled topic sections. These cover introductory courses (including university-level lecture series), interview preparation resources, classical techniques such as linear regression, logistic regression, decision trees, random forests, and support vector machines, and deep learning-specific topics such as convolutional neural networks (used for image tasks), recurrent neural networks and LSTM (used for sequences and language), and autoencoders. There are also sections on natural language processing, computer vision, reinforcement learning, statistics, Bayesian methods, and model validation approaches like cross-validation. You would use this as a study guide if you are starting to learn machine learning and want to find high-quality courses and readings without having to search from scratch, or if you are preparing for data science interviews and need a structured refresher. The full README is longer than what was provided.

Copy-paste prompts

Prompt 1

Using the machine-learning-tutorials list as a syllabus, write me a 4-week self-study plan that takes me from beginner to building a working classification model.

Prompt 2

Explain how convolutional neural networks work for image classification, then give me a PyTorch code example I can run locally.

Prompt 3

Help me prepare for a data science interview: explain the difference between random forests and gradient boosting with a Python scikit-learn example for each.

Prompt 4

Explain how LSTM networks differ from standard RNNs and when to use them for text sequence tasks, with a Python code example.

Prompt 5

Give me a quick guide to cross-validation techniques for model evaluation with Python scikit-learn examples.

Frequently asked questions