Google Professional Machine Learning Engineer
Get started today
Ultimate access to all questions.
Ultimate access to all questions.
A self-driving car company deployed an image segmentation model to enhance its vehicle's navigation system. Post-deployment, the AUC metric showed a significant decline. Further analysis revealed that the model's performance was satisfactory in low-traffic scenarios but deteriorated in high-traffic conditions. Considering the need for the model to perform reliably across varying traffic densities to ensure passenger safety and compliance with regulatory standards, what is the most plausible explanation for this outcome? Choose the best option.
Explanation:
The decline in the AUC metric in high-traffic conditions suggests the model fails to generalize well across different traffic densities. Overfitting in low-traffic areas means the model learns noise as if it were a significant pattern, while underfitting in high-traffic areas indicates it cannot capture the complexity of these scenarios. Additionally, a training dataset biased towards congested areas could exacerbate the model's inability to perform well in less congested scenarios, making both A and C plausible explanations. However, the primary issue is the model's overfitting and underfitting, making A the most accurate answer, with C as a contributing factor.