Deriva — Derive the Algorithm

← Projectsclassifier-lab / L1Score Function~12 min

one move: define the contract

Implement a single neuron from first principles: weighted sum, bias, then ReLU. Make the scalar output explicit before adding training. In the Classifier Lab system, implement this level as a deterministic contract before composing it with the next service.

Required API

def neuron_forward(weights, inputs, bias):
    return activation(weighted_sum)

Behavior

pair each weight with one input
add the bias before activation
ReLU clamps a negative score to zero

Examples — tap to reveal

Constraints

Use only the Python standard library.
Return deterministic values so every run can be compared with the contract.
Do not mutate caller-owned inputs.

Opening…