Amazon has added eight new features to Amazon SageMaker, its end-to-end machine learning (ML) service.

Amazon SageMaker is a fully-managed platform that can be used to build, train, and deploy machine learning models at any scale. It includes hosted Jupyter notebooks for exploring and visualizing your training data stored in Amazon S3. You can connect directly to data in S3, or use AWS Glue to move data from Amazon RDS, Amazon DynamoDB, and Amazon Redshift into S3 for analysis in your notebook.

The first improvement is the addition of Model Cards that can be used to document and review model information. There's also a new Model Dashboard that gives an easier way to track models, monitor performance, and review historical behavior.

For developers, the most interesting addition is improved geospatial support to make it easier to use satellite and location data to make predictions. Amazon says while most data captured has geospatial information, it tends not to be used because geospatial datasets are difficult to work with and can often be petabytes in size. This is exacerbated by customers typically augmenting their proprietary data with third-party data sources like satellite imagery or map data. Until now, developers have had to begin by writing code to divide datasets into manageable subsets, then recombine the subsets to correlate the data and ML model predictions.

Amazon SageMaker now has tools to add in external data, train geospatial models, and visualize the results using APIs with built-in operators to combine these datasets with their own proprietary data. Amazon SageMaker also now comes with pre-trained deep-learning models for uses including agriculture, monitoring areas after natural disasters, and improving urban planning. After training, the built-in visualization tool displays data on a map to uncover new predictions.

SageMaker has also now got new data preparation tools in Amazon SageMaker Studio Notebooks that can be used to visually inspect and address data-quality issues.

Automated model validation has also been added so users can test new models using real-time inference requests.

Amazon SageMaker is available now.

More Information

Amazon SageMaker

Related Articles

Amazon Introduces RStudio on Amazon SageMaker

Sagemaker Studio - An IDE for Machine Learning

To be informed about new articles on I Programmer, sign up for our weekly newsletter, subscribe to the RSS feed and follow us on Twitter, Facebook or Linkedin.

Comments

Make a Comment or View Existing Comments Using Disqus

or email your comment to: comments@i-programmer.info