# \#sci-ml

**URL:** https://si-tesseract.discourse.group/tag/sci-ml/7.md

[Latest](https://si-tesseract.discourse.group/latest.md) · [Categories](https://si-tesseract.discourse.group/categories.md) · [Tags](https://si-tesseract.discourse.group/tags.md)

---

## [Injecting True Physics into Kirigami Generative Design](https://si-tesseract.discourse.group/t/injecting-true-physics-into-kirigami-generative-design/139)

<div class="topic-metadata">

**Author:** [@jkloers](https://si-tesseract.discourse.group/u/jkloers)\
**Replies:** 2\
**Last updated:** [June 16, 2026, 8:43pm UTC](https://si-tesseract.discourse.group/t/injecting-true-physics-into-kirigami-generative-design/139 "2026-06-16T20:43:27Z")

</div>

Hi everyone, I’ve been building an end-to-end differentiable pipeline that designs kirigami — a variant of origami with cuts instead of folds — by gradient descent in JAX. It works very well, but it had a blind spot. E…

---

## [Inverse Burgers with Tesseract: Solver Adjoints, Swappable PINNs, and Amortized Posteriors](https://si-tesseract.discourse.group/t/inverse-burgers-with-tesseract-solver-adjoints-swappable-pinns-and-amortized-posteriors/136)

<div class="topic-metadata">

**Author:** [@julian8897](https://si-tesseract.discourse.group/u/julian8897)\
**Replies:** 2\
**Last updated:** [June 16, 2026, 6:29pm UTC](https://si-tesseract.discourse.group/t/inverse-burgers-with-tesseract-solver-adjoints-swappable-pinns-and-amortized-posteriors/136 "2026-06-16T18:29:58Z")

</div>

This is a follow-up to my Tesseract hackathon honourable mention, tesseract-pinn-inverse-burgers. The original project demonstrated swapping one PINN between JAX and PyTorch. I’ve since rebuilt it around a broader use of…

---

## [Neural network training with Julia](https://si-tesseract.discourse.group/t/neural-network-training-with-julia/47)

<div class="topic-metadata">

**Author:** [@matteo.salvador](https://si-tesseract.discourse.group/u/matteo.salvador)\
**Replies:** 0\
**Last updated:** [February 26, 2025, 1:59pm UTC](https://si-tesseract.discourse.group/t/neural-network-training-with-julia/47 "2025-02-26T13:59:09Z")

</div>

Introduction This example demonstrates how to integrate a Julia-based Multi-Layer Perceptron (MLP) training pipeline with the Tesseract framework. The whole Tesseract can be downloaded here: julia\_mlp.zip (335.5 KB) Re…