Downloads · 30 days
0
mu-net
COINjecture/mu-net
mu-net is a machine learning model from COINjecture. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as mit.
8-layer network with μ^k phase-modulated activations, trained on coherence data.
Access
Public
Updated Apr 3, 2026
Repo size
525 KB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.pt175 KB · 99%
At a glance
- License
- mit
- Access
- Public
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026
- SHA
- e33d4c2f
Model card
From the Hugging Face model README
μ-Net — Eigenverse-Grounded Neural Network
8-layer network with μ^k phase-modulated activations, trained on coherence data.
Architecture
- Layers: 8 (μ⁸ = 1, orbit closure)
- Hidden dim: 64
- Activation: MuActivation (135° phase rotation per layer)
- Loss: MSE + coherence regularization
- Parameters: ~34,954
Results
- R²: 0.9920
- MAE: 0.005367
- Best val loss: 0.000200
- Model coherence: 0.8909
Source
- Eigenverse — 552 Lean theorems, 0 sorry
- COINjecture
- License
- mit
- Created
- Apr 3, 2026
- Updated
- Apr 3, 2026