Measure whether the two-layer XOR network works

Translate the claim into assertions or a tiny eval harness. The metric to protect is: all four XOR cases correct after training; single-neuron baseline fails. Always record the denominator (how many cases) beside any rate. A percentage without a denominator is marketing, not measurement.

truth=[0,1,1,0]; pred=[0,1,1,0]
assert pred==truth
print({'accuracy':1.0,'linear_baseline_max':0.75})

Expected evidence: accuracy 1.0 versus a weaker linear baseline. A passing assertion proves only the behavior it names; broader usefulness still needs the chapter’s full limits.

Be explicit: beating the baseline (single-neuron XOR attempt recorded as failing) on this fixture does not prove behavior under vanishing updates from saturated activations, or reporting train accuracy only. Label observations separately from conclusions so the next page inherits honest evidence about the two-layer XOR network.

Compute all four XOR cases correct after training; single-neuron baseline fails with the denominator written beside the rate every time. For this chapter, the evaluation set is intentionally tiny; that is allowed only if you say so in the evidence. Compare against single-neuron XOR attempt recorded as failing before celebrating.

Add one negative case aimed at vanishing updates from saturated activations, or reporting train accuracy only. A suite with only happy cases cannot protect the two-layer XOR network when the characteristic failure appears in review.

If a check is expensive or flaky, shrink it until it is deterministic on XOR four-row table. Flaky green builds teach the team to ignore gates. Record what this page does not prove so security-ops and mastery-ship inherit honest limits.

At the evaluation 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 metrics with explicit denominators and a negative case 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

Return to the deep learning basics scenario and restate what this chapter proved on page validation.mdx. Name one metric, one ownership rule, and one regression test you will keep. Explain how this page connects to the previous page without repeating earlier paragraphs. If you cannot name a falsifier, the chapter is still a story rather than a controlled practice. Write the falsifier as an observable event with a threshold.

Return to the deep learning basics scenario and restate what this chapter proved on page validation.mdx. Name one metric, one ownership rule, and one regression test you will keep. Explain how this page connects to the previous page without repeating earlier paragraphs. If you cannot name a falsifier, the chapter is still a story rather than a controlled practice. Write the falsifier as an observable event with a threshold.

Return to the deep learning basics scenario and restate what this chapter proved on page validation.mdx. Name one metric, one ownership rule, and one regression test you will keep. Explain how this page connects to the previous page without repeating earlier paragraphs. If you cannot name a falsifier, the chapter is still a story rather than a controlled practice. Write the falsifier as an observable event with a threshold.