Define the single-neuron trainer input contract

The accepted input remains: binary input pairs, target gate outputs, learning rate, epochs. Keep parsing and normalization in functions that do not score, train, or call a model. That split lets a test fail the boundary without blaming the core logic. The user-facing decision stays: learn weights for a linearly separable gate by gradient steps you can print.

import math
def sigmoid(z): return 1/(1+math.exp(-max(-60,min(60,z))))
def forward(x,w,b): return sigmoid(sum(a*c for a,c in zip(x,w))+b)
print(round(forward((1,0),[.2,.2],0),3))

Expected evidence: a probability near 0.55. If the contract is silent on a bad value, later debugging will look like an algorithm bug when it is really a data bug.

Write one assertion for a neighboring valid input to the single-neuron trainer so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of neural-nets-by-building—not as comments you plan to delete.

List every field in AND gate truth table and mark each as required, optional, or forbidden. Required fields must fail loudly when missing; optional fields need defaults you can quote in a test; forbidden fields (secrets, raw PII, path escapes) must never be accepted silently. This list is the contract for the single-neuron trainer.

Add one sentence about encoding, units, or timezones if relevant to binary input pairs, target gate outputs, learning rate, epochs. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to learn weights for a linearly separable gate by gradient steps you can print.

Write the error string you want for the most likely bad input. Prefer ValueError('threshold out of range')-style messages over generic invalid input. The contract’s job is to make learning rate so large weights diverge, or claiming XOR success with one neuron harder to confuse with a model or algorithm bug later.

At the data contract stage for neural-nets-by-building, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about AND gate truth table that later pages inherit without redefining success. Keep that fixture small enough to inspect by hand, keep outputs copy-pasteable as text, and refuse to narrate this baseline as if it were a production SLA: untrained weight predictions on the gate table.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to learn weights for a linearly separable gate by gradient steps you can print. If you cannot point to a file, command, or assertion that proves that for the single-neuron trainer, stay on this page instead of advancing.

Glossary: deep learning · Glossary: gradient descent

Previous · Next