课程定位
CS 277 讨论生成式 AI 和自监督基础模型如何改变医疗。课程覆盖 NLP、CV 和多模态模型,既讲通用模型如何适配医疗,也讲医疗专用 FM,并关注评估、部署和真实临床需求。
主要内容
- 自监督 FM:预训练、表征学习
- 医疗 NLP:临床文本、问答、摘要
- 医疗影像:分类、分割、报告生成
- 多模态:影像 + 文本 + 组学
- 评估与部署:临床指标、监管、偏差
- 伦理与隐私
- 项目
课程大纲 / 课件
以 Winter 2026 公开 calendar 整理;每讲 lecture material 与 recording 在 calendar 页。
先修
CS 229/231N/224N 级 ML 基础。
考核与工作量
作业 + 项目/论文讨论。具体以当季官网为准。
适合谁
医疗 AI、临床数据科学、医疗影像方向;想进入医疗 FM 的工程师/研究者。
学习建议
先修 CS 231N 或 CS 224N。注意医疗数据的隐私和监管约束。
相关课程
官方课程描述(英文原文)
Generative AI and large-scale self-supervised foundation models are poised to have a profound impact on human decision making across occupations. Healthcare is one such area where such models have the capacity to impact patients, clinicians, and other care providers. In this course, we will explore the training, evaluation, and deployment of generative AI and foundation models, with a focus on addressing current and future medical needs. The course will cover models used in natural language processing, computer vision, and multi-modal applications. We will explore the intersection of models trained on non-healthcare domains and their adaptation to domain-specific problems, as well as healthcare-specific foundation models. Prerequisites: Familiarity with machine learning principles at the level of CS 229, 231N, or 224N