Split a single neural network into multiple smaller networks using weight splitting.
-
Updated
Apr 27, 2026 - Jupyter Notebook
Split a single neural network into multiple smaller networks using weight splitting.
Official implementation of the SWAT-NN
A biomimetic, learnable, sparse 3D conductance-based recurrent neural network — used directly as a generative model.
Fully-trainable differentiable logic gate networks with learnable connections - reference implementation of arXiv:2607.09399
Add a description, image, and links to the sparse-networks topic page so that developers can more easily learn about it.
To associate your repository with the sparse-networks topic, visit your repo's landing page and select "manage topics."