Andrew Ng 在 X 上宣布：《Transformers in Practice》新课程上线
TL;DR · AI 摘要
Andrew Ng 推出新课程《Transformers in Practice》，提供对基于 Transformer 的 LLM 工作机制的实践理解。
核心要点
- 课程由 Andrew Ng 和 Sharon Zhou 合作开发，与 AMD 合作推出
- 包含交互式可视化工具，帮助理解注意力机制和量化技术
- 涵盖 LLM 生成过程、幻觉原因及 RAG 技术应用
结构提纲
按章节快速跳转。
- §引言
介绍新课程《Transformers in Practice》及其目标。
- ·课程内容
涵盖 Transformer 工作机制、推理问题诊断和部署优化方法。
- ›教学方式
采用交互式可视化工具增强学习体验。
思维导图
用一张图看清主题之间的关系。
查看大纲文本（无障碍 / 无 JS 友好）
- Transformers in Practice 课程
- 课程目标
- 理解 Transformer 工作机制
- 核心内容
- 注意力机制
- 量化技术
- 教学方式
- 交互式可视化工具
金句 / Highlights
值得收藏与分享的关键句。
课程由 Andrew Ng 和 Sharon Zhou 合作开发，与 AMD 合作推出
包含交互式可视化工具，帮助理解注意力机制和量化技术
涵盖 LLM 生成过程、幻觉原因及 RAG 技术应用
Andrew Ng on X: "New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with @AMD and https://t.co/g8sCrC3sP5" / X
Don’t miss what’s happening
New course: Transformers in Practice. You'll get a practical view of how transformer-based LLMs work, so you can reason about their behavior, diagnose problems like slow inference, and make smarter decisions about deployment. This course is built in partnership with
and taught by
. You'll see how transformers generate text one token at a time, how the model decides which earlier words matter most when predicting the next one, and how techniques like quantization speed up inference on GPUs. This is not a video-only course; interactive visualizations throughout let you play with these concepts and build intuition that sticks. Skills you'll gain: - Understand why LLMs hallucinate, and RAG and chain-of-thought shape what they generate - Look inside the model to see how attention and layers combine to predict the next token - Diagnose inference bottlenecks and learn the techniques that speed up transformers on GPUs Join and understand what's really happening inside your LLMs: https://deeplearning.ai/courses/transf ormers-in-practice…
·
30
82
488
438
Read 30 replies