bootcamp2

Which of the following is true about Feature Cross?

• It is a process of combining features into a single feature

• Feature Cross enables a model to learn separate weights for each combination of features

• Both options are correct

• None of the options are correct

Which of the following is a valid way to reduce training serving skew?

• Use feature store

• Use a transform function (example: TFX or TRANSFORM clause in BQML)

• Use a preprocessing layer within the model

• None of the above

Where are the features registered in a Vertex AI Feature Store?

• Online Store

• Offline Store

• Feature Monitoring

• Feature registry

_____is a collection of semantically related features

• Entity

• Entity type

• Feature Store

• Feature value

Which of the following is the process of importing feature values

computed by your feature engineering jobs into a featurestore?

• Feature ingestion

• Feature Monitoring

• Feature store

• Feature serving

As an approach to feature engineering, which of the following most accurately describes what TensorFlow Transform is a hybrid of?

• Apache Beam on Dataflow and TensorFlow

• AI Platform and TensorFlow

• Dataflow and TensorFlow

• Apache Beam and TensorFlow

You work for a global hotel chain that has recently loaded some guest data into BigQuery. You have experience writing SQL and want to leverage machine learning to help predict guest trends for the next few months. Which option is best?

• Custom training

• BigQuery ML

• Pre-trained APIs

• AutoML

What is the main benefit of using AutoML training?

• It makes the model run faster.

• It deploys the model into production.

• It makes the model perform better.

• It reduces the time it takes to develop trained models and assess their performance

Which of the following is not a key functionality of Vertex AI Model Registry?

• Maintain model documentation

• Govern the model launch process

• Serve ML Features at scale with low latency

• Store model metadata

Model Monitoring measures key model performance metrics and includes:

• Architectural drift, TPU hyperparameter performance, zone outliers and RNNs and CNNS.

• Model drift, model performance, model outliers and data quality.

• Architectural drift, TPU performance, zone outliers and RNNs.

• TPU drift, RNN performance, CPU outliers and data quality.