AWS Machine Learning Blog

Category: Artificial Intelligence

Classifying high-resolution chest x-ray medical images with Amazon SageMaker

Medical image processing is one of the key areas where deep learning is applied to great effect. Typical processing involves classification, detection, and segmentation using various medical image modalities. In this blog post, we outline a method to use the HIPAA Eligible service Amazon SageMaker to train a deep learning model for chest x-ray image […]

Read More

Mapillary uses Amazon Rekognition to work towards building parking solutions for US cities

Mapillary is a collaborative street-level imagery platform that allows people and organizations to upload geo-tagged photos, which can then be used by customers to improve their mapping systems or applications. Mapillary uses Amazon Rekognition, a deep learning-based image and video analysis service, to enhance their metadata extraction. By using the DetectText operation from Amazon Rekognition, […]

Read More

Run SQL queries from your SageMaker notebooks using Amazon Athena

The volume, velocity and variety of data has been ever increasing since the advent of the internet. The problem many enterprises face is managing this “big data” and trying to make sense out of it to yield the most desirable outcome. Siloes in enterprises, continuous ingestion of data in numerous formats, and the ever-changing technology […]

Read More

Get started with automated metadata extraction using the AWS Media Analysis Solution

You can easily get started extracting meaningful metadata from your media files by using the Media Analysis Solution on AWS. The Media Analysis Solution provides AWS CloudFormation templates that you can use to start extracting meaningful metadata from your media files within minutes. With a web-based user interface, you can easily upload files and see the metadata that is automatically extracted. This solution uses Amazon Rekognition for facial recognition, Amazon Transcribe to create a transcript, and Amazon Comprehend to run sentiment analysis on the transcript. You can also upload your own images to an Amazon Rekognition collection and train the solution to recognize individuals. In this blog post, we’ll show you step-by step how to launch the solution and upload an image and video. You’ll be able to see firsthand how metadata is seamlessly extracted.

Read More

No code chatbots: TIBCO uses Amazon Lex to put chat interfaces into the hands of business users

Users today don’t expect to be tied to a desktop computer. They want to interact with systems on the go, in a variety of ways that are convenient to them. This means that people often turn to mobile devices and interact with applications and systems while multi-tasking. Users might not even touch their mobile device while operating the apps they use, particularly when they are in a vehicle, or when they are actively engaged in another activity. In home environments, this “hands-free” capability is facilitated by voice activation systems.

Business users now aspire to the same experience in a business environment. They want to operate the applications and systems that they use in their daily work tasks using voice control, just like they do at home. Imagine how much simpler daily work tasks would be. However, adding voice controls to systems has not been easy. Voice integration can be a very involved project, even for skilled developers. Moreover, today’s business users want to solve their own tactical and strategic business problems by building “low code/no code” apps. Plus, business users want these apps to follow the same end-user requirements we mentioned earlier: They need to be able to be used on the go anywhere, anytime, hands-free.

Read More

Visual search on AWS—Part 2: Deployment with AWS DeepLens

In Part 1 of this blog post series, we examined use cases for visual search and how visual search works. Now we’ll extend the results of Part 1 from the digital world to the physical world using AWS DeepLens, a deep-learning-enabled video camera. Most current applications of visual search don’t involve direct interaction with the physical […]

Read More

Amazon SageMaker runtime now supports the CustomAttributes header

Amazon SageMaker now supports a new HTTP header for the InvokeEndpoint API action called CustomAttributes which can be used to provide additional information about an inference request or response. Amazon SageMaker strips all POST headers except those supported by the InvokeEndpoint API action and you can use the CustomAttributes header to pass custom information such […]

Read More

Visual search on AWS—Part 1: Engine implementation with Amazon SageMaker

In this two-part blog post series we explore how to implement visual search using Amazon SageMaker and AWS DeepLens. In Part 1, we’ll take a look at how visual search works, and use Amazon SageMaker to create a model for visual search. We’ll also use Amazon SageMaker to build a fast index containing reference items to be searched.

Read More

Access Amazon S3 data managed by AWS Glue Data Catalog from Amazon SageMaker notebooks

In this blog post, I’ll show you how to perform exploratory analysis on massive corporate data sets in Amazon SageMaker. From your Jupyter notebook running on Amazon SageMaker, you’ll identify and explore several corporate datasets in the corporate data lake that seem interesting to you. You’ll discover that each contains a subset of the information you need. You’ll join them to extract the interesting information, then continue analyzing and visualizing your data in your Amazon SageMaker notebook, in a seamless experience.

Read More

Pixm takes on phishing attacks with deep learning using Apache MXNet on AWS

Despite numerous cybersecurity efforts, phishing attacks are still on the rise. Phishing is a form of fraud where perpetrators pretend to be reputable companies and attempt to get individuals to reveal personal information, such as passwords and credit card numbers. It’s the most common social tactic.  93 percent of all breaches today start with phishing […]

Read More