PROFESSIONAL-MACHINE-LEARNING-ENGINEER · Question #32
You work for a textile manufacturer and have been asked to build a model to detect and classify fabric defects. You trained a machine learning model with high recall based on high resolution images ta
The correct answer is B. Use the Integrated Gradients method to efficiently compute feature attributions for each predicted. A is not correct because K-fold cross validation offers no explanation on the predictions made by B is correct because it identifies the pixel of the input image that leads to the classification of the C is not correct because PCA simplifies higher dimensional datasets but offers
Question
Options
- AUse K-fold cross validation to understand how the model performs on different test datasets.
- BUse the Integrated Gradients method to efficiently compute feature attributions for each predicted
- CUse PCA (Principal Component Analysis) to reduce the original feature set to a smaller set of
- DUse k-means clustering to group similar images together, and calculate the Davies-Bouldin index
How the community answered
(38 responses)- A3% (1)
- B84% (32)
- C8% (3)
- D5% (2)
Explanation
A is not correct because K-fold cross validation offers no explanation on the predictions made by B is correct because it identifies the pixel of the input image that leads to the classification of the C is not correct because PCA simplifies higher dimensional datasets but offers no added benefit to the scenario. D is not correct because clustering images does not provide any insight into why the classification model made the predictions that it did. https://cloud.google.com/ml-engine/docs/ai-explanations/overview https://storage.googleapis.com/cloud-ai-whitepapers/AI%20Explainability%20Whitepaper.pdf
Topics
Community Discussion
No community discussion yet for this question.