Multiple Choice
You have a demand forecasting pipeline in production that uses Dataflow to preprocess raw data prior to model training and prediction. During preprocessing, you employ Z-score normalization on data stored in BigQuery and write it back to BigQuery. New training data is added every week. You want to make the process more efficient by minimizing computation time and manual intervention. What should you do?
A) Normalize the data using Google Kubernetes Engine.
B) Translate the normalization algorithm into SQL for use with BigQuery.
C) Use the normalizer_fn argument in TensorFlow's Feature Column API. Use the normalizer_fn argument in TensorFlow's Feature Column API.
D) Normalize the data with Apache Spark using the Dataproc connector for BigQuery.
Correct Answer:
Verified
Correct Answer:
Verified
Q2: Your team is working on an NLP
Q3: Your company manages a video sharing website
Q4: You work for a large hotel chain
Q5: You are developing a Kubeflow pipeline on
Q6: You are responsible for building a unified
Q8: You work for a large technology company
Q9: You are training a Resnet model on
Q10: Your team needs to build a model
Q11: You recently joined a machine learning team
Q12: You are training a TensorFlow model on