The scenario involves a machine learning model trained on a dataset requiring computationally expensive preprocessing. The task is to choose the best architecture for deploying this model on Google's AI Platform for online prediction, ensuring the same preprocessing is applied at prediction time.
The suggested answer is B. This option leverages Pub/Sub for message queuing, Dataflow for parallel data processing (the preprocessing step), and AI Platform for model prediction, offering a scalable and efficient solution.
You have trained a model on a dataset that required computationally expensive preprocessing operations. You need to execute the same preprocessing at prediction time. You deployed the model on AI Platform for high-throughput online prediction. Which architecture should you use?
If you often open multiple tabs and struggle to keep track of them, Tabs Reminder is the solution you need. Tabs Reminder lets you set reminders for tabs so you can close them and get notified about them later. Never lose track of important tabs again with Tabs Reminder!
Try our Chrome extension today!
Share this article with your
friends and colleagues.
Earn points from views and
referrals who sign up.
Learn more