---
title: "Discussion on \"Implementing Kolmogorov-Arnold Networks as Dense GEMMs in JAX: A Neural QMC Experiment\" | Hashnode"
description: "Discussion on \"Implementing Kolmogorov-Arnold Networks as Dense GEMMs in JAX: A Neural QMC Experiment\". Replacing B-splines with orthogonal polynomials and jnp.einsum in a Slater–Jastrow–backflow wavefunction for H2."
url: "https://hashnode.com/posts/implementing-kolmogorov-arnold-networks-as-dense-gemms-in-jax-a-neural-qmc-experiment/6aaaafd987de00480675c33a"
---

[Feed](https://hashnode.com/feed) /

Discussion

# [Implementing Kolmogorov-Arnold Networks as Dense GEMMs in JAX: A Neural QMC Experiment](https://samu-physicist.hashnode.dev/implementing-kolmogorov-arnold-networks-as-dense-gemms-in-jax-a-neural-qmc-experiment?utm_source=hashnode&utm_medium=feed)

Replacing B-splines with orthogonal polynomials and jnp.einsum in a Slater–Jastrow–backflow wavefunction for H2.

Sep 16 · 10 min read · samu-physicist.hashnode.dev  
Updated Sep 29  
Read the article

-   [#jax](https://hashnode.com/tag/jax)
-   [#ai-for-science](https://hashnode.com/tag/ai-for-science)
-   [#scientific-computing](https://hashnode.com/tag/scientific-computing)
-   [#deep-learning](https://hashnode.com/tag/deep-learning)
-   [#python](https://hashnode.com/tag/python)

## Written by

[Samu Physicist](https://hashnode.com/@samu-physicist)

@samu-physicist · Tokyo, Japan

  
[View profile](https://hashnode.com/@samu-physicist)

Industrial Chemist, Former Equipment Management & ML Researcher | Architect of FermiKAN

Industrial chemist and former equipment manager turned AI for Science researcher. Passionate about bridging theoretical physical chemistry and modern machine learning. Architect of FermiKAN (a TPU-friendly Neural QMC architecture). Constantly exploring how neuro-symbolic approaches and AI thought partners can push the boundaries of computational chemistry.

## Responses

Markdown supported · ⌘↵ to post

No responses yet.