Machine Learning Courses in cs-video-courses: 120+ Free University Lectures

The cs-video-courses repository aggregates over 120 free machine learning courses in its README.md file, spanning introductory tutorials to advanced PhD-level lectures from universities including Stanford, MIT, and CMU.

The Developer-Y/cs-video-courses repository functions as a curated master index of free computer science education. Located in the README.md file at the repository root, the Machine Learning section (starting around line 398) serves as a single source of truth for learners seeking university-quality video lectures without cost barriers.

Where the Courses Are Listed

All machine learning courses reside in the README.md file under the ### Machine Learning heading. Unlike repositories that split content across multiple files, cs-video-courses maintains one centralized markdown table of contents. The core section spans approximately lines 398 through 520, though related specialized topics appear throughout the document up to line 890.

The entries follow a consistent markdown format: course titles link directly to video playlists or lecture series hosted on platforms like YouTube, university websites, or dedicated course pages.

Machine Learning Course Categories

The repository organizes machine learning courses into distinct pedagogical tracks. Below are the primary categories with representative examples from the source code.

Introductory Machine Learning

For beginners, the list includes foundational courses that require minimal prerequisites. Introduction to Machine Learning for Coders by fast.ai appears at line 399, offering a code-first approach. Statistical Learning from Stanford (line 401) provides statistical foundations, while 10-601 – Intro to ML by Tom Mitchell at CMU (line 405) delivers a classic academic introduction.

Core University CS and EE Courses

This category contains the flagship machine learning courses taught at top computer science departments. CS 229 – Machine Learning from Stanford (line 423) represents the standard undergraduate curriculum. CS 156 – Learning from Data by Yaser Abu-Mostafa at Caltech (line 404) focuses on theoretical underpinnings, while 6.036 – Machine Learning from MIT (line 410) covers algorithmic implementations.

Deep Learning and Neural Networks

Beyond traditional ML, the repository catalogs deep learning intensives. The Deep Learning Boot Camp from the Berkeley Simons Institute (line 403) provides concentrated training on neural architectures. Stanford's CS 229 summer 2019 iteration (line 414) includes dedicated deep learning modules covering convolutional and recurrent networks.

Probabilistic and Graphical Models

Advanced courses focus on probabilistic approaches. Probabilistic Machine Learning from the University of Tübingen (line 665) covers Bayesian methods and Gaussian processes. Statistical Machine Learning from the same institution (line 666) delves into kernel methods and graphical models.

Specialized and Applied Topics

Domain-specific applications appear throughout the list. Machine Learning for Bioinformatics from UIUC (line 419) applies algorithms to genomic data. Machine Learning in IoT (line 671) addresses embedded systems constraints. Applied Machine Learning from Cornell Tech CS 5787 (line 413) emphasizes production deployment and industry workflows.

Summer Schools and Intensive Programs

Short-form educational events supplement semester-long courses. The Mediterranean Machine Learning Summer School 2024 (line 411) and LxMLS Lisbon Machine Learning School 2024 (line 412) offer compressed curricula taught by leading researchers, typically spanning one to two weeks of intensive instruction.

Graduate and PhD-Level Material

Advanced offerings target researchers and doctoral students. CMU 10-701 – Advanced ML (line 408) covers theoretical foundations at the PhD level. Stanford CS 229M – ML Theory from Fall 2021 (line 722) explores statistical learning theory and optimization landscapes. UC Berkeley CS 189/289A – Intro to ML (line 890) provides graduate-level mathematical rigor.

Extracting Machine Learning Courses Programmatically

To programmatically access the course catalog, you can parse the README.md file directly. The following Python script isolates the Machine Learning section and extracts all HTTP/HTTPS URLs:

import pathlib
import re

# Path to the README (adjust if you cloned elsewhere)

readme_path = pathlib.Path("README.md")

# Load the file

text = readme_path.read_text(encoding="utf-8")

# Isolate the Machine Learning block (starts with "### Machine Learning")

ml_block = re.search(r"### Machine Learning(.+?)(?:\n### |\Z)", text, re.S).group(1)

# Extract every markdown link that ends with a URL

urls = re.findall(r"\[.+?\]\((https?://[^)]+)\)", ml_block)

# Print formatted list

for i, u in enumerate(urls, 1):
    print(f"{i:3}. {u}")

Running this script against the repository root generates a numbered list of all machine learning course URLs, enabling integration with learning management systems or automated playlist generation. The regex pattern specifically targets the markdown link syntax used throughout README.md, capturing video lecture links while excluding internal anchors.

Summary

• The cs-video-courses repository maintains the definitive list of free machine learning video lectures in its README.md file.
• The Machine Learning section contains over 120 distinct courses ranging from fast.ai's introductory series to CMU's PhD-level advanced seminars.
• Course categories span introductory coding, core university curricula, deep learning, probabilistic models, and domain-specific applications like bioinformatics.
• Specific line references (e.g., line 423 for Stanford CS 229, line 410 for MIT 6.036) allow direct navigation to particular entries.
• The entire catalog can be extracted programmatically using standard Python regex against the markdown source.

Frequently Asked Questions

How many machine learning courses are listed in the cs-video-courses repository?

The repository contains more than 120 distinct machine learning courses in the Machine Learning section of README.md. This count includes full semester courses, summer school intensives, and specialized workshops from universities worldwide.

Are all machine learning courses in the repository free to access?

Yes, according to the repository's curation standards, every listed machine learning course links to freely available video lectures. The repository specifically excludes paid or restricted content, focusing on open educational resources from institutions like Stanford, MIT, CMU, and Berkeley.

Does the repository include deep learning courses or only traditional machine learning?

The list includes both traditional machine learning and modern deep learning content. Courses like the Deep Learning Boot Camp from Berkeley Simons Institute (line 403) and deep learning modules within Stanford's CS 229 (line 414) cover neural networks, CNNs, and RNNs alongside classical algorithms like SVMs and random forests.

How can I find the most recently added machine learning courses?

Since all courses reside in the single README.md file, you can check the git commit history for recent changes to that specific file. New courses are typically appended to their respective categories, with summer schools and workshops (like the Mediterranean ML Summer School 2024 at line 411) representing the most current additions.

{
  "mcpServers": {
    "instagit": {
      "command": "npx",
      "args": ["-y", "instagit@latest"]
    }
  }
}