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。

Ask HN: What are the best environments for differential programming?

4 点作者 pc2g4d将近 3 年前
I want to incorporate an algebra solver into a neural network. Crazy idea, I know. I&#x27;m trying to generate algebra problems that are actually solvable, and the best way I can think to do that would be to have a solver implemented in-network. That&#x27;s a complex piece of code, thus the interest in differentiable programming.<p>Julia? Python? Swift? Something else?<p>My experience has been that the autogradient in TensorFlow would be way too finicky to implement something complex in. Maybe I&#x27;m wrong?

1 comment

ChrisRackauckas将近 3 年前
Algebra solver, as in solving algebraic equations numerically? The Julia SciML ecosystem has libraries like DeepEquilibiurmNetworks.jl for building neural networks with nonlinear algebraic equation solving as part of the networks (<a href="https:&#x2F;&#x2F;deepequilibriumnetworks.sciml.ai&#x2F;stable&#x2F;manual&#x2F;nlsolve&#x2F;" rel="nofollow">https:&#x2F;&#x2F;deepequilibriumnetworks.sciml.ai&#x2F;stable&#x2F;manual&#x2F;nlsol...</a>).
评论 #32431904 未加载