
Ultimate access to all questions.
You are a Machine Learning Engineer working on an image segmentation model for a self-driving car application. After deploying the first version of the model, you observe a significant decline in the area under the curve (AUC) metric. Upon further investigation through video recordings, you notice that the model's performance is suboptimal in scenarios with highly congested traffic, whereas it performs as expected in less congested conditions. Considering the need for the model to perform reliably across all traffic conditions to ensure safety and compliance with regulatory standards, what is the most probable cause for this outcome? Choose the best option.
A
The model is overfitting to less congested traffic scenarios, leading to poor generalization in highly congested conditions.
B
The training dataset was predominantly composed of data from congested traffic scenarios, causing the model to underperform in less congested conditions.
C
The AUC metric is not suitable for evaluating the performance of image segmentation models in autonomous driving applications.
D
The model suffers from the vanishing gradient problem, which impedes learning from highly congested traffic scenarios.
E
Both A and D are correct.