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

# threshold-2to4decoder

2-to-4 binary decoder. Converts 2-bit input to one-hot 4-bit output.

## Function

decode(A1, A0) -> [Y0, Y1, Y2, Y3]

Yi = 1 iff input = i

## Truth Table

| A1 | A0 | Y0 | Y1 | Y2 | Y3 |
|----|----|----|----|----|-----|
| 0 | 0 | 1 | 0 | 0 | 0 |
| 0 | 1 | 0 | 1 | 0 | 0 |
| 1 | 0 | 0 | 0 | 1 | 0 |
| 1 | 1 | 0 | 0 | 0 | 1 |

## Architecture

Single layer with 4 neurons. Each Yi matches pattern i.

| Output | Weights [A1, A0] | Bias |
|--------|------------------|------|
| Y0 | [-1, -1] | 0 |
| Y1 | [-1, +1] | -1 |
| Y2 | [+1, -1] | -1 |
| Y3 | [+1, +1] | -2 |

## Parameters

| | |
|---|---|
| Inputs | 2 |
| Outputs | 4 |
| Neurons | 4 |
| Layers | 1 |
| Parameters | 12 |
| Magnitude | 12 |

## Usage

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

w = load_file('model.safetensors')

def decode2to4(a1, a0):
    inp = torch.tensor([float(a1), float(a0)])
    return [int((inp * w[f'y{i}.weight']).sum() + w[f'y{i}.bias'] >= 0) for i in range(4)]

print(decode2to4(1, 0))  # [0, 0, 1, 0] - input 2
```

## License

MIT