CS224N: NLP with Deep Learning

by Stanford University

AdvancedCourseFreeFull university course

Stanford's flagship NLP course — word vectors to transformers and LLMs, with rigor.

Start LearningReviewed July 3, 2026

Overview

CS224N is the academic gold standard for natural language processing with deep learning. It progresses from word vectors and RNNs to attention, transformers, pretraining, and modern LLMs, with mathematically rigorous lectures and substantial coding assignments. Lecture videos, slides, and notes are freely available online. Choose it when you want research-grade depth on how language models are built and trained.

At a Glance

Topic
Models
Level
Advanced
Format
Course
Cost
Free
Duration
Full university course
Provider
Stanford University
Hands-on
Yes — code/exercises
Certificate
None

What You’ll Learn

  • Word embeddings and sequence models
  • Attention and the transformer architecture
  • Pretraining and modern LLMs
  • NLP tasks and evaluation

Highlights

  • Stanford graduate-level rigor
  • Free lectures, slides, and assignments

Who It’s For

Best For

  • Learners wanting deep, research-grade NLP knowledge

Prerequisites

  • Python
  • Calculus/linear algebra
  • ML basics

FAQ

What is CS224N: NLP with Deep Learning?

Materials and recorded lectures for Stanford's graduate NLP course covering embeddings, attention, transformers, and large language models.

Is CS224N: NLP with Deep Learning free?

CS224N: NLP with Deep Learning is free to access.

What level is CS224N: NLP with Deep Learning for?

CS224N: NLP with Deep Learning is aimed at a advanced audience. Recommended background: Python, Calculus/linear algebra, ML basics.

How long does CS224N: NLP with Deep Learning take?

Expect roughly Full university course. Most learners work through it at their own pace.

What will I learn from CS224N: NLP with Deep Learning?

You'll learn: Word embeddings and sequence models; Attention and the transformer architecture; Pretraining and modern LLMs; NLP tasks and evaluation.

Topics

NLPtransformersStanfordembeddingsLLM