Protocol
Convolutions and Residual Vision Models
Reproduce a small residual-learning comparison and identify a vision failure category that accuracy hides. Include representative errors with data provenance.
40–70 active hours60–90 min sessionsIntermediate
Mastery contract
Core protocol · Standard 1.0 · Reproduce a small residual-learning comparison and identify a vision failure category that accuracy hides. Include representative errors with data provenance.
Loading your learning records…
Reasoning — not yet passed
Compute all shapes/receptive fields correctly and distinguish equivariance from invariance.
Reliable implementation — not yet passed
The convolution agrees with the library on a small fixture; finite differences check selected kernel entries.
Reproducible experiment — not yet passed
Plain and residual models share data and budget; reduced-scale results are not called full ResNet reproduction.
Defense and handoff — not yet passed
Defend the architecture comparison using learning curves, error categories and the cost of each improvement.
All four criteria must pass. Activity completion does not satisfy them.
An independent reviewer reruns your work and varies something you did not rehearse: a fresh input, a different working directory, or a declared edge case.
Pilot decisions are provisional, not external credentials. For an appeal or sensitive artifact, contact your designated pilot operator with the submission ID. Export your assessment history.
What you will do
6 total
Derive convolution output dimensions and receptive fields for a 3-layer network; explain the residual gradient path.
Implement a small NumPy convolution and compare forward/gradient results with PyTorch; train a compact plain CNN and matched residual variant.
Use CIFAR-10 or a documented subset with 3 seeds per architecture; freeze augmentations and report accuracy, parameter count and training work.
Debug incorrect padding and train/test normalization mismatch; visualize the affected border outputs and feature distributions.
Write a 500–900 word technical report linking the reasoning, code, measurements, and limitations; include the project decision below.
Assess all 4 mastery criteria against saved artifacts, request an independent review, and repeat each failed criterion on a fresh example.
Essentials
A reading session alone never satisfies a mastery criterion.
Store source references, assumptions, and artifact paths beside every result.
Keep an untouched check case that differs from the worked example.
Record all attempts, including failures and results that contradict your prediction.
Use the stated comparison conditions; document every deviation before drawing a conclusion.
Protocol guardrails
Do
- +State the expected result before running the comparison.
- +Keep one minimal reproducible failing case when debugging.
- +Record environment versions and the exact command used.
- +Compare explanations with saved intermediate values.
- +Ask a reviewer to challenge the weakest assumption.
Don't
- ×Do not copy a worked solution and present it as an independent implementation.
- ×Do not tune against held-out evaluation outcomes.
- ×Do not report only the best seed or discard inconvenient runs.
- ×Do not equate elapsed hours or a completed run with a passed assessment.
- ×Do not conceal reduced-scale experiments behind claims about the original full-scale result.
Protocol authorship
Written by NuthinButta as instructional design. The teaching sources are the official references linked in each milestone; the exercises, workload and pass thresholds are ours, not their authors'.