Threshold Logic Circuits
Collection
Boolean gates, voting functions, modular arithmetic, and adders as threshold networks.
•
248 items
•
Updated
•
1
At least 4 of 5 inputs high.
4outof5(a, b, c, d, e) = 1 if (a + b + c + d + e) >= 4, else 0
Single neuron: weights [1, 1, 1, 1, 1], bias -4
Fires when: sum >= 4
| Inputs | 5 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 6 |
| Magnitude | 9 |
from safetensors.torch import load_file
import torch
w = load_file('model.safetensors')
def atleast4of5(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(atleast4of5(0, 0, 1, 1, 1)) # 0 (sum=3)
print(atleast4of5(0, 1, 1, 1, 1)) # 1 (sum=4)
MIT