Threshold Logic Circuits
Collection
Boolean gates, voting functions, modular arithmetic, and adders as threshold networks.
•
248 items
•
Updated
•
1
4-bit zero detector. Outputs 1 if all 4 input bits are zero.
iszero4(a, b, c, d) = 1 if (a + b + c + d) == 0, else 0
Equivalent to 4-input NOR gate.
Single neuron: weights [-1, -1, -1, -1], bias 0
Fires when: -a - b - c - d + 0 >= 0, i.e., all inputs are 0.
| Inputs | 4 |
| Outputs | 1 |
| Neurons | 1 |
| Layers | 1 |
| Parameters | 5 |
| Magnitude | 4 |
from safetensors.torch import load_file
import torch
w = load_file('model.safetensors')
def iszero4(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(iszero4(0, 0, 0, 0)) # 1 (is zero)
print(iszero4(0, 0, 0, 1)) # 0 (not zero)
MIT