Stanford AI 课程地图 EN GitHub ↗
← 返回课程地图
Stanford · 2026—27 CS 236 基础核心 ★★★★☆

核心课程 · 基础核心

深度生成模型

Deep Generative Models

深度生成模型的理论课:VAE、GAN、flow、diffusion 的概率基础与训练算法。

3 学分 2027 春 Letter or Credit/No Credit ★★★★☆
生成模型Diffusion概率

课程定位

CS 236 是生成模型方向最系统的课程之一,由 Stefano Ermon 讲授。它从概率建模和变分推断出发,覆盖 VAE、GAN、normalizing flow、energy-based model、diffusion/score matching,数学要求较高。

主要内容

  1. 概率基础:极大似然、变分推断、ELBO、MCMC
  2. VAE:重参数化、后验坍塌、层次化 VAE
  3. GAN:对抗训练、模式崩溃、Wasserstein GAN
  4. Flow 模型:可逆变换、Jacobian、连续流
  5. Energy-based 模型:对比散度、score matching
  6. Diffusion:DDPM、score-based、classifier-free guidance
  7. 应用:图像、文本、语音、RL
  8. 项目:生成模型的研究或应用

课程大纲 / 课件

#主题 / 讲者
01Introduction; Probability and Linear Algebra
02Background + Autoregressive Models
03Maximum Likelihood Learning + VAEs
04VAEs + Normalizing Flows
05Normalizing Flows + GANs
06GANs + Energy Based Models
07Energy Based Models + Score Based Models
08Energy Based Models + Evaluation of Generative Models
09Score Based Diffusion Models + Discrete Latent Variable Models
10Diffusion Models for Discrete Data

以 Fall 2023 公开 syllabus 整理;当前学期以课程站为准。

先修

CS 221/228/229/230 至少一门;概率与微积分;Python 编程。

考核与工作量

作业 + 期中/期末 + 项目;数学推导和实现并重。具体以当季官网为准。

适合谁

想做扩散模型、图像/视频生成、生成式 AI 研究的人;想理解 VAE/GAN 背后概率原理的人。

学习建议

先补变分推断和 score matching,否则 diffusion 部分会很吃力。配合 CS 236G 可以补 GAN 的工程细节。

相关课程

官方课程描述(英文原文)

Generative models are widely used in many subfields of AI and Machine Learning. Recent advances in parameterizing these models using neural networks, combined with progress in stochastic optimization methods, have enabled scalable modeling of complex, high-dimensional data including images, text, and speech. In this course, we will study the probabilistic foundations and learning algorithms for deep generative models, including Variational Autoencoders (VAE), Generative Adversarial Networks (GAN), and flow models. The course will also discuss application areas that have benefitted from deep generative models, including computer vision, speech and natural language processing, and reinforcement learning. Prerequisites: Basic knowledge about machine learning from at least one of CS 221, 228, 229 or 230. Students will work with computational and mathematical models and should have a basic knowledge of probabilities and calculus. Proficiency in some programming language, preferably Python, required.