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

# threshold-atmost2outof4

At most 2 of 4 inputs high.

## Function

atmost2outof4(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 | 1 |
| 0 | 0 | 0 | 1 | 1 | 1 |
| 0 | 0 | 1 | 1 | 2 | 1 |
| 0 | 1 | 1 | 1 | 3 | 0 |
| 1 | 1 | 1 | 1 | 4 | 0 |

## Architecture

Single neuron: weights [-1, -1, -1, -1], bias 2

Fires when: -a - b - c - d + 2 >= 0, i.e., sum <= 2

## Parameters

| | |
|---|---|
| Inputs | 4 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 5 |
| Magnitude | 6 |

## Usage

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

w = load_file('model.safetensors')

def atmost2of4(a, b, c, d):
    inp = torch.tensor([float(a), float(b), float(c), float(d)])
    return int((inp @ w['neuron.weight'].T + w['neuron.bias'] >= 0).item())

print(atmost2of4(0, 0, 1, 1))  # 1 (sum=2)
print(atmost2of4(0, 1, 1, 1))  # 0 (sum=3)
```

## License

MIT