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

# threshold-atmost3outof5

At most 3 of 5 inputs high.

## Function

atmost3outof5(a, b, c, d, e) = 1 if (a + b + c + d + e) <= 3, else 0

## Truth Table (selected)

| sum | out |
|-----|-----|
| 0 | 1 |
| 1 | 1 |
| 2 | 1 |
| 3 | 1 |
| 4 | 0 |
| 5 | 0 |

## Architecture

Single neuron: weights [-1, -1, -1, -1, -1], bias 3

Fires when: -a - b - c - d - e + 3 >= 0, i.e., sum <= 3

## Parameters

| | |
|---|---|
| Inputs | 5 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 6 |
| Magnitude | 8 |

## Usage

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

w = load_file('model.safetensors')

def atmost3of5(a, b, c, d, e):
    inp = torch.tensor([float(a), float(b), float(c), float(d), float(e)])
    return int((inp @ w['neuron.weight'].T + w['neuron.bias'] >= 0).item())

print(atmost3of5(1, 1, 1, 0, 0))  # 1 (sum=3)
print(atmost3of5(1, 1, 1, 1, 0))  # 0 (sum=4)
```

## License

MIT