Google Cloud Professional Machine Learning Engineer — Question 89

You recently built the first version of an image segmentation model for a self-driving car. After deploying the model, you observe a decrease in the area under the curve (AUC) metric. When analyzing the video recordings, you also discover that the model fails in highly congested traffic but works as expected when there is less traffic. What is the most likely reason for this result?

Answer options

• A. The model is overfitting in areas with less traffic and underfitting in areas with more traffic.
• B. AUC is not the correct metric to evaluate this classification model.
• C. Too much data representing congested areas was used for model training.
• D. Gradients become small and vanish while backpropagating from the output to input nodes.

Correct answer: A

Explanation

The correct answer is A, as it indicates that the model has learned too well from the training data in low-traffic scenarios, failing to generalize to the complexities of high-traffic environments. Answer B is incorrect because AUC can still be a valid metric for evaluating classification models. Answer C is misleading, as using too much data for congested areas would typically help the model perform better in those situations. Answer D relates to a different issue in deep learning and does not apply to the model's performance in this context.