AWS Mobile Back-End Framework Adds Machine Learning Functionality
- By David Ramel
- August 7, 2019
The Amazon cloud is continuing its mission "to put machine learning in the hands of every developer" with new functionality for AWS Amplify, a back-end development framework for mobile and Web apps.
Amplify debuted back in 2015 when it was called Mobile Hub. AWS describes it as "an opinionated set of libraries, UI components, and a command-line interface to build an app backend and integrate it with your iOS, Android, Web, and React Native apps."
Amplify provides the usual back-end resources and services such as storage, authentication & authorization, APIs (GraphQL and REST), analytics, push notifications, chat bots, augmented reality, virtual reality -- and more recently, machine learning functionality.
Pre-trained AI services available on the AWS platform provide capabilities such as image and video analysis, natural language, personalized recommendations, virtual assistants and forecasting that developers can infuse into their applications without needing deep expertise in AI, machine learning and so on.
Now AWS has added a Predictions category to those services that lets developers configure an app to:
- Identify text, entities, and labels in images using Amazon Rekognition, or identify text in scanned documents to get the contents of fields in forms and information stored in tables using Amazon Textract.
- Convert text into a different language using Amazon Translate, text to speech using Amazon Polly, and speech to text using Amazon Transcribe.
- Interpret text to find the dominant language, the entities, the key phrases, the sentiment, or the syntax of unstructured text using Amazon Comprehend.
"It has never been easier to add machine learning functionalities to a Web or mobile app," said AWS evangelist Danilo Poccia, who details how to do just that in a July 31 blog post.
Mobile developers, meanwhile, can use the new iOS and Android SDK for SageMaker to make inference requests on their SageMaker-hosed custom models with an HTTPS endpoint. "The Android SDK also includes support for Amazon Textract that allows developers to extract text and data from scanned documents. These services add to the list of existing AI services supported in iOS and Android SDKs."
More information is available in the following resources:
David Ramel is an editor and writer for Converge360.