Q
What is the easiest way to access
AWS infrastructures?
Dr. Bratin Saha: The easiest way to use any of the
infrastructures we've described is through Amazon
SageMaker, a fully managed service that helps you
build, train, and deploy ML models.
When you're ready to train in Amazon SageMaker,
simply specify the location of your data in (Amazon
Simple Storage Service) Amazon S3, indicate the type
and quantity of instance you need, and get started
with a single click. Amazon SageMaker sets up a
distributed compute cluster, performs the training,
outputs the result to Amazon S3, and tears down the
cluster when complete.
Amazon SageMaker makes it easy to deploy your
trained model into production with a single clickâso
you can start generating predictions for real-time
or batch data quickly. You can one-click deploy your
model onto autoscaling Amazon ML instances across
multiple availability zones for high redundancy.
Amazon SageMaker will launch the instances, deploy
your model, and set up the secure HTTPS endpoint for
your application.
To help you get the most out of your ML infrastructure,
Amazon SageMaker also offers software innovations.
Many of the most common use cases for ML, such as
personalization, require you to manage anywhere from
a few hundred to hundreds of thousands of models. For
example, taxi services train custom models based on each
city's traffic patterns to predict rider wait times. While
this approach leads to higher prediction accuracy, the
downside is that the cost to deploy the models increases
significantly because you have to use one endpoint per
model. Amazon SageMaker multi-model endpoints allow
you to deploy thousands of models behind a single
endpoint, reducing cost by orders of magnitude.
If you want to get up to speed quickly on Amazon
SageMaker, check out the new Practical Data Science
Specialization on Coursera.
11
