Google Professional Machine Learning Engineer Question 57
Select 3Google Cloud PlatformYou are tasked with building a machine learning model to classify customer feedback into positive, negative, or neutral categories. Your team has decided to use AutoML in Google Cloud to simplify the process. Which considerations should you prioritize before starting the model training with AutoML?
- A
Ensuring that the dataset is uploaded to a Google Cloud Storage bucket and properly labeled.
- B
Selecting the specific algorithm to use within AutoML based on the dataset.
- C
Verifying that your dataset meets the minimum data size and diversity requirements for AutoML to work effectively.
- D
Defining the evaluation metrics you want AutoML to optimize for, such as accuracy or precision.
- E
Manually tuning hyperparameters for the AutoML training process.
Show answer and explanation
Correct answers: A, C, D
Explanation
When using AutoML, it is crucial to focus on preparing a high-quality dataset, ensuring it meets AutoML's minimum requirements, and defining evaluation metrics that align with your goals. AutoML automates tasks such as algorithm selection and hyperparameter tuning, so these do not require manual input.
- A. Correct.
Correct: AutoML requires a well-prepared and labeled dataset, which must be stored in a Google Cloud Storage bucket for training.
- B. Incorrect.
Incorrect: AutoML abstracts the algorithm selection process, so you do not need to choose a specific algorithm.
- C. Correct.
Correct: AutoML has minimum data size and diversity requirements to ensure the model can be trained effectively.
- D. Correct.
Correct: While AutoML automates many processes, you must define the evaluation metrics to ensure the model aligns with your business objectives.
- E. Incorrect.
Incorrect: Hyperparameter tuning is handled automatically by AutoML, so manual tuning is not required.