Module 2 Rubric#
Artifact#
gradient trace report comparing manual reasoning with autograd output
Criterion |
Excellent |
Satisfactory |
Needs Revision |
|---|---|---|---|
Technical correctness |
Neural-network concepts, code, metrics, and terminology are accurate for backpropagation and automatic differentiation. |
Most technical claims are accurate, with minor gaps or imprecision. |
Claims are incorrect, unsupported, or disconnected from the module lab. |
Experimental evidence |
Uses notebook results, plots, and comparisons to support a clear argument; identifies what the toy setup proves and does not prove. |
Uses notebook evidence but interpretation or limits are incomplete. |
Reports outputs without analysis, comparison, or limitations. |
Design tradeoffs |
Explains architecture, optimization, data, compute, or deployment tradeoffs in concrete terms. |
Names tradeoffs but does not fully connect them to design decisions. |
Treats model choices as arbitrary or self-evident. |
Risk and failure analysis |
Identifies technical and operational failure modes, including overfitting, data mismatch, compute limits, or misuse where relevant. |
Identifies some failure modes but mitigations are generic. |
Omits meaningful failure analysis. |
Communication |
Recommendation is concise, reproducible, and understandable to an AI engineering reviewer. |
Recommendation is understandable but partially supported. |
Recommendation overclaims or cannot be reproduced from the submitted evidence. |
Minimum Completion Standard#
A passing submission must include runnable notebook evidence, at least one baseline or parameter comparison, one documented limitation of the toy setup, and a recommendation for the next experiment or deployment gate.
100-Point Scoring Guide#
Use this 100-point guide to plan and self-check your submission. The qualitative rubric above defines the performance levels; the table below shows how each criterion contributes to the total.
Criterion |
Points |
How to self-check |
|---|---|---|
Technical correctness |
20 |
Full criterion credit requires evidence that meets the Excellent description; use the other descriptions to identify what to revise before submission. |
Experimental evidence |
25 |
Full criterion credit requires evidence that meets the Excellent description; use the other descriptions to identify what to revise before submission. |
Design tradeoffs |
20 |
Full criterion credit requires evidence that meets the Excellent description; use the other descriptions to identify what to revise before submission. |
Risk and failure analysis |
20 |
Full criterion credit requires evidence that meets the Excellent description; use the other descriptions to identify what to revise before submission. |
Communication |
15 |
Full criterion credit requires evidence that meets the Excellent description; use the other descriptions to identify what to revise before submission. |
Performance Bands#
Band |
Points |
Interpretation |
|---|---|---|
Excellent |
90-100 |
Graduate-level command; evidence is accurate, contextualized, and professionally defensible. |
Proficient |
80-89 |
Meets graduate expectations with minor gaps in depth, precision, or integration. |
Developing |
70-79 |
Demonstrates partial outcome achievement but needs revision for rigor, evidence, or communication. |
Not Yet Demonstrated |
Below 70 |
Does not yet provide adequate evidence of the aligned course outcomes. |
🧑🌾 SAMWISE — Pre-Submission Self-Check#
🧑🌾 SAMWISE — Student note
Before submitting, point to specific artifact evidence for every criterion. Confirm that another reader can reproduce or inspect it, that your recommendation follows from it, and that you name at least one limitation and one responsible next step.
Use the performance bands honestly: revise a criterion when your evidence matches Satisfactory, Developing, or Not Yet Demonstrated rather than relying on polished prose to cover a missing result.
This is prewritten guidance; it does not provide answers or predict a grade.