1
Assert interfaces
Write expected tensor shapes for input, logits, labels, and gradients.
Required evidence: Passing shape and finite-value assertions.
0/80 minimum characters
Builder mini-project·90-120 minutes
Neural Network Debugging Project
Repair a broken training loop using shape checks, gradient evidence, a tiny-batch test, and learning curves.
Scenario
A binary MLP remains at chance accuracy. You are given a tiny deterministic case and must identify whether the defect is in the forward pass, loss, gradients, or update.
You will demonstrate
- Use invariants to localize training defects.
- Verify gradients independently.
- Separate optimization health from generalization.
Project evidence
Show the work, not a checked box.
Each response is stored in this browser as you type. Include metrics, test output, or a decision rationale wherever the deliverable asks for it.
2
Check a gradient
Compare the analytical scalar gradient with a centered finite difference.
Required evidence: Relative error below the stated tolerance.
0/80 minimum characters
3
Overfit a tiny batch
Show that loss can decrease substantially on a deterministic subset.
Required evidence: Loss trace and final predictions.
0/80 minimum characters
4
Write the diagnosis
Name the defect, evidence, correction, and a regression test.
Required evidence: A falsifiable root-cause note.
0/80 minimum characters
Runnable Python lab
Repair a broken scalar update
Implement the gradient and update needed to fit a one-weight model.
Project defense
What should be checked first when a tiny MLP cannot overfit eight deterministic examples?
Rubric self-review
Rate the evidence, not your effort: 0 missing, 1 weak, 2 adequate, 3 strong. All criteria must be reviewed, but a low honest score does not get hidden.
Assertions localize failures.
Gradient parity uses a stated tolerance.
The tiny-batch test is deterministic.
The fix includes a regression check.
Useful references
Project completion gate
Completion is controlled by stored evidence, deterministic tests, a decision defense, rubric review, and the artifact when required.
Evidence pendingCode pendingDefense pendingRubric pending
Optional cloud portfolio
Submit evidence across devices.
An account is required. Submit only when the local completion gate passes. AI review is advisory and separate from deterministic completion.