Threshold Logic Circuits
Collection
Boolean gates, voting functions, modular arithmetic, and adders as threshold networks.
•
269 items
•
Updated
•
1
At most 2 of 5 inputs high.
atmost2outof5(a, b, c, d, e) = 1 if (a + b + c + d + e) <= 2, else 0
| sum | out |
|---|---|
| 0 | 1 |
| 1 | 1 |
| 2 | 1 |
| 3 | 0 |
| 4 | 0 |
| 5 | 0 |
Single neuron: weights [-1, -1, -1, -1, -1], bias 2
Fires when: -a - b - c - d - e + 2 >= 0, i.e., sum <= 2
| Inputs | 5 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 6 |
| Magnitude | 7 |
from safetensors.torch import load_file
import torch
w = load_file('model.safetensors')
def atmost2of5(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(atmost2of5(1, 1, 0, 0, 0)) # 1 (sum=2)
print(atmost2of5(1, 1, 1, 0, 0)) # 0 (sum=3)
MIT