TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

Show HN: minigrad – a minimal, educational autograd library (~100 loc in Python)

5 点作者 jellyksong将近 5 年前

1 comment

paperwork将近 5 年前
I love this. The code is simple and documented. However, whenever I’ve tried to understand autograd, I get stuck at dual numbers.<p>As a programmer, I understand building up a computation graph where each node is some sort of an elementary function which knows how to take its own gradient. So a constant&#x2F;scalar node has derivative&#x2F;gradient of zero, x^n has derivative of nx^(n-1), etc. these gradients are passed from the end to the beginning according to the chain rule, etc., etc.<p>However, autograd is not supposed to be the symbolic differentiation we learned in high school.<p>This project doesn’t seem to have anything to do with duals...confused!
评论 #23345783 未加载