|
|
"""
|
|
|
Threshold Network for AND Gate
|
|
|
|
|
|
A formally verified single-neuron threshold network computing logical conjunction.
|
|
|
Weights are integer-constrained and activation uses the Heaviside step function.
|
|
|
"""
|
|
|
|
|
|
import torch
|
|
|
from safetensors.torch import load_file
|
|
|
|
|
|
|
|
|
class ThresholdAND:
|
|
|
"""
|
|
|
AND gate implemented as a threshold neuron.
|
|
|
|
|
|
Circuit: output = (w1*x1 + w2*x2 + bias >= 0)
|
|
|
With weights=[1,1], bias=-2: only (1,1) reaches threshold.
|
|
|
"""
|
|
|
|
|
|
def __init__(self, weights_dict):
|
|
|
self.weight = weights_dict['weight']
|
|
|
self.bias = weights_dict['bias']
|
|
|
|
|
|
def __call__(self, x1, x2):
|
|
|
inputs = torch.tensor([float(x1), float(x2)])
|
|
|
weighted_sum = (inputs * self.weight).sum() + self.bias
|
|
|
return (weighted_sum >= 0).float()
|
|
|
|
|
|
@classmethod
|
|
|
def from_safetensors(cls, path="model.safetensors"):
|
|
|
return cls(load_file(path))
|
|
|
|
|
|
|
|
|
def forward(x, weights):
|
|
|
"""
|
|
|
Forward pass with Heaviside activation.
|
|
|
|
|
|
Args:
|
|
|
x: Input tensor of shape [..., 2]
|
|
|
weights: Dict with 'weight' and 'bias' tensors
|
|
|
|
|
|
Returns:
|
|
|
AND(x[0], x[1])
|
|
|
"""
|
|
|
x = torch.as_tensor(x, dtype=torch.float32)
|
|
|
weighted_sum = (x * weights['weight']).sum(dim=-1) + weights['bias']
|
|
|
return (weighted_sum >= 0).float()
|
|
|
|
|
|
|
|
|
if __name__ == "__main__":
|
|
|
weights = load_file("model.safetensors")
|
|
|
model = ThresholdAND(weights)
|
|
|
|
|
|
print("AND Gate Truth Table:")
|
|
|
print("-" * 25)
|
|
|
for x1 in [0, 1]:
|
|
|
for x2 in [0, 1]:
|
|
|
out = int(model(x1, x2).item())
|
|
|
expected = x1 & x2
|
|
|
status = "OK" if out == expected else "FAIL"
|
|
|
print(f"AND({x1}, {x2}) = {out} [{status}]")
|
|
|
|
