JAX-FEM: A differentiable GPU-accelerated 3D finite element solver for automatic inverse design and mechanistic data science · HackerPapers discussionshttps://hackerpaper.kaipfister.de/p/2212.00964/Collected HN comments and submissions linking this paper.enMon, 02 Nov 2026 11:16:22 GMTJAX-FEM: A differentiable GPU-accelerated 3D finite element solver for automatic inverse design and mechanistic data science — mentioned by heisenzombiehttps://news.ycombinator.com/item?id=41117393urn:hackerpapers:mention:2212.00964:41117393Wed, 31 Jul 2024 08:41:16 GMT<p>Paper describing this and what it’s for here: https://arxiv.org/pdf/2212.00964 (PDF) We emphasize the following three features that differentiate JAX-FEM from other FEM libraries: 1. Efficient solution to forward PDE with GPU acceleration; 2. Differentiable simulation for automatic inverse design; 3. Seamless integration with machine learning</p><p><a href="https://hackerpaper.kaipfister.de/p/2212.00964/">Paper and discussion history</a>. A mention is not an endorsement.</p>cs.MS