Threshold Logic Circuits
Collection
Boolean gates, voting functions, modular arithmetic, and adders as threshold networks.
•
248 items
•
Updated
•
1
At least 1 of 4 inputs high. Equivalent to 4-input OR gate.
1outof4(a, b, c, d) = 1 if (a + b + c + d) >= 1, else 0
Equivalently: OR(a, b, c, d)
| a | b | c | d | sum | out |
|---|---|---|---|---|---|
| 0 | 0 | 0 | 0 | 0 | 0 |
| 0 | 0 | 0 | 1 | 1 | 1 |
| 0 | 0 | 1 | 1 | 2 | 1 |
| 0 | 1 | 1 | 1 | 3 | 1 |
| 1 | 1 | 1 | 1 | 4 | 1 |
Single neuron: weights [1, 1, 1, 1], bias -1
Fires when: a + b + c + d - 1 >= 0, i.e., sum >= 1
| Inputs | 4 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 5 |
| Magnitude | 5 |
from safetensors.torch import load_file
import torch
w = load_file('model.safetensors')
def atleast1of4(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(atleast1of4(0, 0, 0, 0)) # 0
print(atleast1of4(0, 0, 0, 1)) # 1
MIT