TE
TechEcho
Home24h TopNewestBestAskShowJobs
GitHubTwitter
Home

TechEcho

A tech news platform built with Next.js, providing global tech news and discussions.

GitHubTwitter

Home

HomeNewestBestAskShowJobs

Resources

HackerNews APIOriginal HackerNewsNext.js

© 2025 TechEcho. All rights reserved.

Designing bridge trusses with Pytorch autograd

82 pointsby eschluntzover 1 year ago
You can use Pytorch for more than just Neural Networks - its autograd is super powerful for any problem where you need gradients (and are too lazy to calculate them yourself...)!

5 comments

eschluntzover 1 year ago
Author here. Yep, obviously this is more commonly done with dedicated optimization libraries, but the fun part was doing it in Pytorch to use autograd and as a way to visualize optimizers etc :)
评论 #38960798 未加载
评论 #38969637 未加载
HumblyTossedover 1 year ago
I forgot the name of the software but when I took statics way back in the day we used an app that let us design the bridge and then it animated a truck going across. It was cute but it also highlighted (literally) all the areas that were in stress during crossing. I enjoyed that class - it was interesting even if it had nothing to do with programming. :)
评论 #38962215 未加载
评论 #38967571 未加载
评论 #38961661 未加载
评论 #38961611 未加载
评论 #38962657 未加载
dwrodriover 1 year ago
I remember several years ago when differentiable programming was an object of interest to the programming community and Lattner was trying to make Swift for Tensorflow happen[1].<p>I&#x27;m of the opinion that it was ahead of its time: Swift hadn&#x27;t (and still hasn&#x27;t) made enough progress on Linux support for it to be taken seriously as a language for writing anything that isn&#x27;t associated with Apple. However, as a result, Swift now has language-level differentiability in its compiler. I&#x27;d love to see Swift get used for projects like this, but I suppose the reality of the matter is that there are so many performant runtimes for 2D&#x2F;3D physics that there just isn&#x27;t much of a need for automatic differentiation (and its overhead) to solve these problems. The tooling nerd in me thinks this stuff is fascinating.<p><a href="https:&#x2F;&#x2F;github.com&#x2F;tensorflow&#x2F;swift">https:&#x2F;&#x2F;github.com&#x2F;tensorflow&#x2F;swift</a>
评论 #38961529 未加载
评论 #38960938 未加载
评论 #38964790 未加载
评论 #38961125 未加载
fritzoover 1 year ago
&gt; You can use Pytorch for more than just Neural Networks<p>Facts. Pytorch is such a fun too for applied calculus. Just write down a program, compute its derivative, and do any of the fun things you can do with derivatives, like optimization or linear approximation.
评论 #38960974 未加载
londons_exploreover 1 year ago
I want someone to do this for a fluid dynamics problem.<p>I suspect lots of things in everyday life could be made substantially better&#x2F;cheaper&#x2F;more efficient if entire system optimization like this could be done to their design.
评论 #38962161 未加载
评论 #38962743 未加载
评论 #38961598 未加载