You have recently developed a custom model for image classification by using a neural network. You need to automatically identify the values for learning rate, number of layers, and kernel size. To…

Question

Options

• ATrain an AutoML image classification model.
• BCreate a custom training job that uses the Vertex AI Vizier SDK for parameter optimization.
• CCreate a Vertex AI hyperparameter tuning job.
• DCreate a Vertex AI pipeline that runs different model training jobs in parallel.

• A
  7% (3)
• B
  17% (8)
• C
  72% (33)
• D
  4% (2)

Explanation

Hyperparameter tuning-automatically searching for optimal values of learning rate, number of layers, and kernel size-is exactly what Vertex AI Hyperparameter Tuning is built for. It runs multiple trials in parallel using Bayesian optimization or other search strategies, and integrates with your existing training code via minimal SDK calls. Option A (AutoML) trains Googleʼs own model architecture and cannot tune a custom neural network you have already built. Option B (Vertex AI Vizier SDK) provides similar optimization but requires more custom integration code than the native hyperparameter tuning job. Option D (Vertex AI pipeline with parallel jobs) requires substantial pipeline orchestration code and does not provide built-in parameter search logic. Option C provides the purpose-built, low-code solution.

No community discussion yet for this question.