← Free Learning Library

Machine Learning

Stanford CS229: Machine Learning Foundations

A full graduate-level machine learning course from Stanford Online, covering supervised learning, unsupervised learning, neural networks, and reinforcement learning.

Learn from: the original creator. Original content published on YouTube. DigitalSkillX organizes these public resources into a structured learning path. DigitalSkillX does not claim ownership or partnership.

Lessons
17
Time
About 20 hr 36 min
Level
advanced

Now playing: Stanford CS229 Machine Learning | Spring 2026 | Lecture 13: LLMs, Next-Word Prediction Loss

About this path

This learning path follows the Stanford CS229 Machine Learning lecture series from Spring 2026, taught through Stanford Online. It starts with the supervised learning setup and builds through linear models, generative methods, neural networks, unsupervised learning, and modern topics like diffusion models and transformers. The later lectures move into reinforcement learning. The course is mathematically dense and assumes comfort with linear algebra, probability, and calculus, so it works best for learners who want a rigorous treatment rather than a quick overview. Note that a few lecture numbers are missing from the playlist, and some later lecture titles repeat earlier topic names, which may reflect re-recorded or mislabeled sessions.

What you will learn

  • Explain the supervised learning setup and the bias-variance tradeoff
  • Apply least squares, logistic regression, and generalized linear models
  • Describe generative learning methods such as Gaussian discriminant analysis
  • Build and train basic neural networks, including backpropagation
  • Use clustering and dimensionality reduction techniques like k-means, GMMs, and PCA
  • Understand modern architectures including diffusion models, transformers, and LLMs
  • Explain core reinforcement learning ideas such as policy gradient

Who this is for

Learners ready for a deeper, more challenging free learning path.

Curriculum

Section 1: Foundations of Supervised Learning

  1. Lesson 1: Stanford CS229 Machine Learning | Spring 2026 | Lecture 1: Introduction

    This opening lecture introduces the CS229 course and the broad field of machine learning. It sets expectations for the mathematical level of the course and outlines the main topic areas that will be covered.

    Open on YouTube
  2. Lesson 2: Stanford CS229 Machine Learning | Spring 2026 | Lecture 2: Supervised Learning Setup

    This lecture lays out the formal supervised learning setup, including notation for training data, hypotheses, and loss functions. It introduces the basic framework used throughout the rest of the course.

    Open on YouTube
  3. Lesson 3: Stanford CS229 Machine Learning | Spring 2026 | Lecture 3: Weighted Least Squares

    This lecture covers weighted least squares, an extension of ordinary least squares that lets different training examples carry different weights. It connects the method to probabilistic assumptions about the data.

    Open on YouTube
  4. Lesson 4: Stanford CS229 Machine Learning | Spring 2026 | Lecture 4: Exponential Family, GLMs Classification

    This lecture introduces the exponential family of distributions and generalized linear models. It shows how linear regression and logistic regression fit into a single modeling framework.

    Open on YouTube
  5. Lesson 5: Stanford CS229 Machine Learning | Spring 2026 | Lecture 5: Gaussian Discriminant Analysis

    This lecture covers Gaussian discriminant analysis, a generative approach to classification. It contrasts generative and discriminative methods and works through the Gaussian case in detail.

    Open on YouTube

Section 2: Practical Advice and Neural Networks

  1. Lesson 6: Stanford CS229 Machine Learning | Spring 2026 | Lecture 6: Dataset Split, ML Advice

    This lecture focuses on dataset splitting and practical advice for machine learning projects. It discusses how to diagnose bias and variance problems and what to try next when a model underperforms.

    Open on YouTube
  2. Lesson 7: Stanford CS229 Machine Learning | Spring 2026 | Lecture 7: Neural Networks 1 (Architecture)

    The first of two lectures on neural networks, this session covers network architecture. It introduces layers, activation functions, and how neural networks represent functions.

    Open on YouTube
  3. Lesson 8: Stanford CS229 Machine Learning | Spring 2026 | Lecture 8: Neural Networks 2 (Backprop)

    This lecture covers backpropagation, the algorithm used to train neural networks. It walks through the chain rule and how gradients are computed layer by layer.

    Open on YouTube

Section 3: Unsupervised Learning and Representation

  1. Lesson 9: Stanford CS229 Machine Learning | Spring 2026 | Lecture 9: K-Means and GMM (non-EM)

    This lecture introduces unsupervised learning through k-means clustering and Gaussian mixture models without the EM algorithm. It covers the basic clustering problem and the k-means procedure.

    Open on YouTube
  2. Lesson 10: Stanford CS229 Machine Learning | Spring 2026 | Lecture 10: GMM (EM), PCA

    This lecture covers Gaussian mixture models with the EM algorithm and principal component analysis. It explains how EM handles latent variables and how PCA reduces dimensionality.

    Open on YouTube
  3. Lesson 11: Stanford CS229 Machine Learning | Spring 2026 | Lecture 11: Diffusion Models

    This lecture introduces diffusion models, a class of generative models that learn to reverse a noising process. It covers the main ideas behind denoising diffusion and how samples are generated.

    Open on YouTube
  4. Lesson 12: Stanford CS229 Machine Learning | Spring 2026 | Lecture 12: Representation Learning

    This lecture covers representation learning, the problem of learning useful features from data. It discusses why good representations matter and surveys common approaches.

    Open on YouTube

Section 4: Language Models and Transformers

  1. Lesson 13: Stanford CS229 Machine Learning | Spring 2026 | Lecture 13: LLMs, Next-Word Prediction Loss

    This lecture introduces large language models and the next-word prediction loss used to train them. It explains how language modeling is framed as a prediction problem.

    Open on YouTube
  2. Lesson 14: Stanford CS229 Machine Learning | Spring 2026 | Lecture 14: Transformers, In-Context Learning

    This lecture covers transformers and in-context learning. It explains the attention mechanism and how transformer models can adapt to new tasks from examples in the prompt.

    Open on YouTube

Section 5: Reinforcement Learning and Additional Lectures

  1. Lesson 15: Stanford CS229 Machine Learning | Spring 2026 | Lecture 16: Basic Concept in RL, Policy Gradient

    This lecture introduces reinforcement learning, covering basic concepts and the policy gradient method. It explains the agent-environment loop and how policies can be improved directly.

    Open on YouTube
  2. Lesson 16: Stanford CS229 Machine Learning | Spring 2026 | Lecture 18: GMM (EM), PCA

    This lecture is labeled as covering Gaussian mixture models with EM and PCA. The title repeats an earlier topic, so the exact content may overlap with or extend the earlier lectures on these methods.

    Open on YouTube
  3. Lesson 17: Stanford CS229 Machine Learning | Spring 2026 | Lecture 20: GMM (EM), PCA

    This lecture is also labeled as covering Gaussian mixture models with EM and PCA. As with the previous lecture, the repeated title suggests the content may revisit or extend earlier material on these topics.

    Open on YouTube

Your progress

0 of 17 lessons completed (0%).

Complete this learning path to become eligible for your DigitalSkillX certificate.

Related learning