APPLICATION OF SUPERVISED LEARNING
MACHINE LEARNING PIPELINE
|
Question
[CLICK ON ANY CHOICE TO KNOW THE RIGHT ANSWER]
|
A team of Data Scientists wants to use Amazon SageMaker training jobs to run two different versions of the same model in parallel to compare the long-term effectiveness of the different versions in reaching the related business outcome.How should the team deploy these two model versions with minimum management?
|
|
Create a Lambda function that preprocesses the incoming data, calls a single Amazon SageMaker endpoints for the two models, and finally returns the prediction.
|
|
|
Create an endpoint configuration with production variants for the two models with equal weights.
|
|
|
Create an endpoint configuration with production variants for the two models with a weight ratio of 90:10.
|
|
|
Create a Lambda function that downloads the models from Amazon S3 and calculates and returns the predictions of the two models.
|
Explanation:
Detailed explanation-1: -A machine learning pipeline is the end-to-end construct that orchestrates the flow of data into, and output from, a machine learning model (or set of multiple models). It includes raw data input, features, outputs, the machine learning model and model parameters, and prediction outputs.
There is 1 question to complete.