Category: Amazon Machine Learning

Organizations hosting customer-specific machine learning models on AWS have unique isolation and performance requirements and require a solution that provides a scalable, high-performance, and feature-rich ML platform. Learn how Amazon SageMaker Pipelines helps you to pre-process data, build, train, tune, and register ML models in SaaS applications. We’ll focus on best practices for building tenant-specific ML models with particular focus on tenant isolation and cost attribution.

Healthcare customers are adopting fast healthcare interoperability resources (FHIR) as a way to exchange healthcare information in a secure and compliant manner. Aligning on a common data model streamlines healthcare application development and the adoption of machine learning. Learn how to visualize and navigate FHIR data on AWS by using eSante Clarity, Cognosante’s FHIR viewer. Clarity can access FHIR data on AWS and navigate the clinical dataset within.

Recognizing a user’s signature is an essential step in banking and legal transactions, and typically involves relying on human verification. Learn how Capgemini uses machine learning from AWS to build ML-models to verify signatures from different user channels including web and mobile apps. This ensures organizations can meet the required standards, recognize user identity, and assess if further verifications are needed.

The continuous interaction between humans and animals in slaughterhouses can lead to animal welfare deviations which can occur in different forms. Learn how Deloitte’s AI4Animals solution is capable of detecting these welfare deviations in order to improve the conditions of animals in slaughterhouses. This is accomplished by using AWS Panorama, a machine learning appliance and software developer kit (SDK) that allows organizations to bring computer vision to their on-premises cameras.

Increasing penetration of analytics in the life sciences industry is expected to drive significant growth for businesses in the coming years. Learn about Accenture’s life sciences data and analytics accelerator which enables customers to respond to these challenges and use data for their competitive advantage. Particular focus is given to the commercial domain and use of analytics to increase customer engagement and optimize sales and marketing.

Kubernetes is hardware-agnostic and can work across a wide range of infrastructure platforms, and Kubeflow—the self-described machine learning toolkit for Kubernetes—provides a Kubernetes-native platform for developing and deploying ML systems. Learn how D2iQ Kaptain on AWS directly addresses the challenges of moving ML workloads into production, the steep learning curve for Kubernetes, and the particular difficulties Kubeflow can introduce.

Learn about the AWS AI services stack for government agencies and partners to develop intelligent automation solutions to extract information from digitalized paper documents. Intelligent Document Processing (IDP) is a solution that enables extraction and processing of specific data elements from documents using AI and machine learning techniques. AWS services that add AI/ML intelligence to IDP solutions include Amazon Textract, Amazon Comprehend, Amazon Augmented AI, and Amazon Kendra.

We are excited to introduce AI for data analytics (AIDA) partner solutions which embed predictive analytics into mainstream analytics workspaces. These AI/ML solutions from AWS Partners have interfaces and integrations that help bring predictive analytics into the normal workflow of business experts. AWS AIDA includes partner solutions from Amplitude, Anaplan, Causality Link, Domo, Exasol, InterWorks, Pegasystems, Provectus, Qlik, Snowflake, Tableau, TIBCO, and Workato.

Dataiku orchestrates the entire machine learning lifecycle and makes it accessible to data scientists and analysts alike. With deep integration with AWS AI tools, Dataiku enables users to augment their analytics workflow with pretrained NLP and computer vision models. Learn how you can use Amazon Comprehend and Amazon Rekognition plugins on Dataiku Data Science Studio (DSS) to build a simple workflow of NLP and computer vision use cases, respectively.

Building effective machine learning models requires storing and managing historical data, but conventional databases can quickly become a nightmare to regulate. Queries start taking too long, for example, slowing down business decisions. Learn how to use Amazon Redshift ML and Query Editor V2 to create, train, and apply ML models to predict diabetes cases for a sample diabetes dataset. You can follow a similar approach to address other use cases such as customer churn prediction and fraud detection.