Explain how selective label correction on misclassified examples alters estimated dev set performance.
Question: Analyze the mathematical or statistical impact of only fixing labels on dev set examples that your model misclassified. How does this practice skew the measured performance compared to the true performance of the system?
Sample answer: Fixing only the misclassified examples selectively changes errors into correct classifications in the dataset. Because we do not inspect or correct mislabeled examples that the system happened to classify correctly, we only decrease the count of measured errors and never increase it. This artificially inflates the measured accuracy of the model, creating an optimistic bias where the dev set accuracy looks higher than it actually is.
Key points:
- Only the labels of misclassified dev examples are inspected and corrected.
- Mislabeled dev examples that the model classified as correct remain uninspected and uncorrected.
- This selective process artificially inflates the measured dev set performance, introducing evaluation bias.
Rubric: The response must explain: 1. Only error counts are reduced because only misclassified examples are inspected. 2. Correctly classified examples with incorrect labels are left uncorrected. 3. This selective correction results in an artificially high (optimistically biased) measured dev set accuracy.
0
1
Tags
Machine Learning
Deep Learning
Supervised Learning
Dive into Deep Learning @ D2L
Data Science
Machine Learning Strategy
Related
Practical Convenience Causes Label-Correction Bias in Dev Sets
When Label-Correction Bias Is Acceptable Versus Problematic
What risk arises when you fix label errors only for the dev-set examples your classifier misclassified?
True or False: Correcting mislabeled dev-set examples only where your system was wrong produces an unbiased evaluation.
Fixing labels only on examples your system _____ can introduce bias into dev-set evaluation.
Why does fixing labels only on misclassified dev examples introduce bias into the evaluation?
Fixing labels only on misclassified dev examples can introduce bias into your evaluation.
To avoid label-correction bias, you should review labels of _____ dev examples, not only misclassified ones.
Match each label-correction practice to its effect on dev set evaluation bias.
Order the steps a team should follow when correcting dev set labels to avoid introducing bias.
What is the most likely effect on measured dev set accuracy when labels are corrected only on misclassified examples?
Reviewing only the dev examples your model misclassified is sufficient to ensure an unbiased dev set evaluation.
Label-correction bias arises because mislabeled examples the system classified _____ are never reviewed or fixed.
Match each term related to label-correction bias to its correct definition.
Order the reasoning steps that explain why fixing only misclassified labels introduces bias into dev set evaluation.
Explain how selective label correction on misclassified examples alters estimated dev set performance.
Evaluating a team's decision to correct only misclassified dev set labels.
State the primary risk of fixing only misclassified dev set labels.