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

# threshold-exactly2outof4

Exactly 2 of 4 inputs high.

## Function

exactly2outof4(a, b, c, d) = 1 if (a + b + c + d) == 2, else 0

## Truth Table

| a | b | c | d | sum | out |
|---|---|---|---|-----|-----|
| 0 | 0 | 0 | 0 | 0 | 0 |
| 0 | 0 | 0 | 1 | 1 | 0 |
| 0 | 0 | 1 | 1 | 2 | 1 |
| 0 | 1 | 0 | 1 | 2 | 1 |
| 1 | 0 | 0 | 1 | 2 | 1 |
| 0 | 1 | 1 | 0 | 2 | 1 |
| 1 | 0 | 1 | 0 | 2 | 1 |
| 1 | 1 | 0 | 0 | 2 | 1 |
| 0 | 1 | 1 | 1 | 3 | 0 |
| 1 | 1 | 1 | 1 | 4 | 0 |

## Architecture

```
Layer 1:
  N1: [1,1,1,1] b=-2  (fires when sum >= 2)
  N2: [-1,-1,-1,-1] b=2  (fires when sum <= 2)

Layer 2:
  AND: [1,1] b=-2  (fires when both N1 and N2 fire)
```

## Parameters

| | |
|---|---|
| Inputs | 4 |
| Outputs | 1 |
| Neurons | 3 |
| Layers | 2 |
| Parameters | 13 |
| Magnitude | 16 |

## Usage

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

w = load_file('model.safetensors')

def exactly2of4(a, b, c, d):
    inp = torch.tensor([float(a), float(b), float(c), float(d)])
    l1 = (inp @ w['layer1.weight'].T + w['layer1.bias'] >= 0).float()
    out = (l1 @ w['layer2.weight'].T + w['layer2.bias'] >= 0).float()
    return int(out.item())

print(exactly2of4(0, 0, 1, 1))  # 1
print(exactly2of4(0, 1, 1, 1))  # 0
```

## License

MIT