---
license: mit
tags:
- pytorch
- safetensors
- threshold-logic
- neuromorphic
- voting
---

# threshold-2outof6

At-least-2-of-6 threshold gate. Fires when 2 or more of the 6 inputs are high.

## Function

```
2outof6(x0, x1, x2, x3, x4, x5) = 1 if (x0 + x1 + x2 + x3 + x4 + x5) >= 2
```

## Truth Table (selected)

| Hamming Weight | Output |
|:--------------:|:------:|
| 0 | 0 |
| 1 | 0 |
| 2 | 1 |
| 3 | 1 |
| 4 | 1 |
| 5 | 1 |
| 6 | 1 |

## Mechanism

Single threshold neuron with uniform weights. The bias of -2 sets the firing threshold:

- Sum = (number of 1s) + (-2)
- Fires when sum >= 0, i.e., when Hamming weight >= 2

## k-out-of-6 Family

| Circuit | Bias | Fires when |
|---------|------|------------|
| 1-out-of-6 | -1 | HW >= 1 |
| 2-out-of-6 | -2 | HW >= 2 |
| 3-out-of-6 | -3 | HW >= 3 (majority) |
| 4-out-of-6 | -4 | HW >= 4 |
| 5-out-of-6 | -5 | HW >= 5 |
| 6-out-of-6 | -6 | HW = 6 (AND) |

## Parameters

| | |
|---|---|
| Weights | [1, 1, 1, 1, 1, 1] |
| Bias | -2 |
| Inputs | 6 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 7 |
| Magnitude | 8 |

## Usage

```python
from safetensors.torch import load_file
import torch

w = load_file('model.safetensors')

def at_least_2_of_6(bits):
    inputs = torch.tensor([float(b) for b in bits])
    return int((inputs @ w['neuron.weight'].T + w['neuron.bias'] >= 0).item())

print(at_least_2_of_6([1, 1, 0, 0, 0, 0]))  # 1
```

## License

MIT