Artificial Intelligence R&D

ARTIFICIAL INTELLIGENCE RESEARCH & DEVELOPMENT

Keep up with the latest AI, ML and data science research from WWT

What We Do

The AI R&D program at WWT is an applied research initiative focused on investigating the one to three-year horizon of the artificial intelligence (AI) and machine learning (ML) space. The program develops and conducts internal projects grounded in WWT's deep understanding of industry use cases.

Our people

AI R&D is an initiative formed by WWT individuals interested in the future of AI and ML. It functions as a rotational program with an Operations team and an R&D Working team composed of data scientists, data engineers and application engineers.

Our platform

Our AI R&D platform is a cloud-based containerized environment that gives us the extensibility and elasticity to develop, build and test AI/ML solutions. The platform's flexible architecture optimizes network and storage, while GPU-enabled devices provide the technical capabilities for algorithm training. ML infrastructure tools are deployed on top of the AI R&D platform to streamline workflows and automate the productionalization of projects from dataset to deployment.

Our projects

All AI R&D projects — which are developed, funded and conducted internally — are geared toward applied research that unearths scientific discoveries in the AI/ML space that are innovative, solve problems and have potential commercial application. Industry use cases and datasets — from mining, motorsports, utilities and more — power our AI R&D work.

Our output

The goal of WWT's AI R&D program is to produce reusable platform, workflow and algorithm components that can be leveraged for future AI/ML project work or as demos in our Advanced Technology Center (ATC). All projects result in a white papers made accessible to our customers and the wider AI community. Explore our latest findings below.

AI R&D White Papers

Machine Learning Models for Route Consolidation

Learn how our experts developed a generalizable machine learning method for route consolidation using a deep autoencoder, k-means clustering and Procrustes analysis.

Obscuring and Analyzing Sensitive Info with Generative Adversarial Networks

White paper explores feasibility of generating representative data for two data types: binary input from medical records and real-valued sensor data from industrial mining trucks.

Deep Learning with NVIDIA DGX-1

White paper highlight some practical considerations for the Deep Learning practitioner relevant to neural network training on the NVIDIA DGX-1.

ML for Shovel Tooth Failure Detection

Mining shovels suffer from a prohibitively high false-positive rate (FPR) of 25%. Learn how advanced technology can reduce the FPR to 5% in this white paper.

ATC Connect Recommendation Engine

White paper explores how a hybrid recommendation engine was built for recommending relevant articles to the users of the WWT ATC Connect mobile app.

Image Classification of Race Cars

White paper explores the use of artificial intelligence to perform an image sorting task to gain a competitive edge in a NASCAR race.

A New Use for Autoencoders in the Utility Industry

Learn how WWT experts are leveraging neural network autoencoders and k-means clustering to segment energy consumers based on meter reading data.

Training an AI Model Using Fake Images from Generative Adversarial Networks

White paper discusses methods to use artificial intelligence to generate representative data that can be used safely for research and analysis.