Skip to content
@occamolab

OccamoLab

A research group composing neural networks with known laws: small, exact, auditable models.
README.md

OccamoLab

A research group composing neural networks with known laws: small, exact, auditable models.

Website: occamolab.org · Paper: arXiv:2611.12567 · Code: lawkan

Research interests

  • Group-law layers and geometric deep learning
  • Robot-arm calibration and inertial navigation
  • Parameter-efficient models for edge and embedded deployment

Contact

hello@occamolab.org · Commercial licensing of the LawKAN code is available on request.

Pinned Loading

  1. lawkan lawkan Public

    Code and reproduction artifact for LawKAN: exact group-law layers for transformation composition, with all experiments, pinned dumps, checks, and figure generators.

    Python

Repositories

Showing 3 of 3 repositories

People

This organization has no public members. You must be a member to see who’s a part of this organization.

Top languages

Loading…

Most used topics

Loading…