Define the two-layer XOR network input contract

The accepted input remains: XOR truth table, hidden width, 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: show why a hidden layer is required for XOR while keeping the net tiny.

def relu(x): return max(0,x)
def forward(x):
 h=[relu(x[0]-x[1]),relu(x[1]-x[0])]
 return h, h[0]+h[1]
print(forward((1,0)))

Expected evidence: hidden (1, 0) and score 1. 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 two-layer XOR network so tightening the boundary does not over-reject. Document field names and types the way a teammate would need them on day two of deep-learning-basics—not as comments you plan to delete.

List every field in XOR four-row 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 two-layer XOR network.

Add one sentence about encoding, units, or timezones if relevant to XOR truth table, hidden width, learning rate, epochs. Contracts that ignore units create “correct” programs that still ship wrong decisions when someone tries to show why a hidden layer is required for XOR while keeping the net tiny.

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 vanishing updates from saturated activations, or reporting train accuracy only harder to confuse with a model or algorithm bug later.

At the data contract stage for deep-learning-basics, the job is narrower than finishing a product demo. You are creating one progressive evidence piece about XOR four-row 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: single-neuron XOR attempt recorded as failing.

For this page specifically, success looks like malformed inputs rejected with field-named errors while still centering the user decision to show why a hidden layer is required for XOR while keeping the net tiny. If you cannot point to a file, command, or assertion that proves that for the two-layer XOR network, stay on this page instead of advancing.

Glossary: deep learning · Glossary: loss function

Previous · Next