threshold-atmost4outof5

At most 4 of 5 inputs high. Equivalent to 5-input NAND gate.

Function

atmost4outof5(a, b, c, d, e) = 1 if (a + b + c + d + e) <= 4, else 0

Equivalently: NAND5(a, b, c, d, e) = NOT(a AND b AND c AND d AND e)

Truth Table (selected)

sum	out
0	1
1	1
2	1
3	1
4	1
5	0

Architecture

Single neuron: weights [-1, -1, -1, -1, -1], bias 4

Fires when: -a - b - c - d - e + 4 >= 0, i.e., sum <= 4

Parameters

Inputs	5
Outputs	1
Neurons	1
Layers	1
Parameters	6
Magnitude	9

Usage

from safetensors.torch import load_file
import torch

w = load_file('model.safetensors')

def atmost4of5(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(atmost4of5(1, 1, 1, 1, 0))  # 1 (sum=4)
print(atmost4of5(1, 1, 1, 1, 1))  # 0 (sum=5)

License

MIT