threshold-3outof8

At-least-three detector. Fires when 3 or more of 8 inputs are set.

Circuit

  x₀ x₁ x₂ x₃ x₄ x₅ x₆ x₇
   │  │  │  │  │  │  │  │
   └──┴──┴──┴──┼──┴──┴──┴──┘
               ▼
          ┌─────────┐
          │ w: all 1│
          │ b:  -3  │
          └─────────┘
               │
               ▼
            HW ≥ 3

Mechanism

• Sum = (number of 1s) - 3
• Fires when Hamming weight ≥ 3

Two active inputs aren't enough. Needs a third to cross threshold.

k-out-of-8 Family

Circuit	Bias	Fires when
1-out-of-8	-1	HW ≥ 1
2-out-of-8	-2	HW ≥ 2
3-out-of-8	-3	HW ≥ 3 (this)
4-out-of-8	-4	HW ≥ 4
...	...	...

Parameters

Weights	[1, 1, 1, 1, 1, 1, 1, 1]
Bias	-3
Total	9 parameters

Usage

from safetensors.torch import load_file
import torch

w = load_file('model.safetensors')

def at_least_3(bits):
    inputs = torch.tensor([float(b) for b in bits])
    return int((inputs * w['weight']).sum() + w['bias'] >= 0)

Files

threshold-3outof8/
├── model.safetensors
├── model.py
├── config.json
└── README.md

License

MIT