Build the first working two-layer XOR network

Build only what the claim requires: two-layer net reaches XOR solutions that a single neuron cannot. Prefer boring, deterministic code over frameworks you cannot yet explain. Run the path twice; identical output on this fixture is a feature, not a lack of creativity.

def xor_net(x):
 h1=max(0,x[0]-x[1]); h2=max(0,x[1]-x[0])
 return int(h1+h2>=.5)
print([xor_net(x) for x in [(0,0),(0,1),(1,0),(1,1)]])

Expected evidence: dead or dimensionally broken network. Read each printed intermediate as part of the argument that the path works—not as decoration.

Narrate the journey from raw input to result for a single example from XOR four-row table. If you cannot name an intermediate, the implementation is still too opaque for this lab. Only after this path is solid should you generalize data sources or UI.

While implementing the two-layer XOR network, print or log at least three intermediates that map to the claim (two-layer net reaches XOR solutions that a single neuron cannot). Good intermediates are values a teammate could recompute with a calculator or diff. Bad intermediates are framework traces you cannot explain.

Re-run with XOR four-row table twice. If the second run differs, either the path is nondeterministic (document the seed) or you have hidden global state—both are lab bugs until named.

Stop adding features once the path supports show why a hidden layer is required for XOR while keeping the net tiny. Extra UI, extra tools, or extra models belong in later chapters. The mastery bar for this page is simply: a deterministic end-to-end path with intermediates.

At the implementation 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 a deterministic path with printed intermediates 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