You are using Vertex AI and TensorFlow to build a custom image-classification model. You need the model’s decisions and their rationale to be understandable to your company’s stakeholders. You also want to examine the results to identify any issues or possible biases. What should you do?
A
Use TensorFlow to generate and visualize features and statistics.2. Analyze the results together with the standard model evaluation metrics.
B
Use TensorFlow Profiler to visualize the model execution.2. Analyze the relationship between incorrect predictions and execution bottlenecks.
C
Use Vertex Explainable AI to generate example-based explanations.2. Visualize the results of sample inputs from the entire dataset together with the standard model evaluation metrics.
D
Use Vertex Explainable AI to generate feature attributions. Aggregate feature attributions over the entire dataset.2. Analyze the aggregation result together with the standard model evaluation metrics.
Show Answer Answer Explanation Vertex Explainable AI feature attributions show how input features contribute to predictions. Aggregating attributions across the full dataset reveals global feature influence and can surface concerning patterns or potential bias; standard model evaluation metrics are still required to assess predictive quality. Google Cloud documentation notes that attributions alone cannot determine whether a model is fair, unbiased, or high quality, and should be considered with evaluation metrics.
Learn more
Community Discussion