Too often, companies run models in production without adequately managing the risk of model drift. Or to manage it, they rely on data scientists doing manual and time-consuming work, distracting resources from future research and innovation. This whitepaper describes the common reasons and types of drift, and provides an overview of best practices for mitigating the risk of drift and monitoring to detect drift early.
Spark is a distributed computing framework that has skyrocketed in popularity over the last several years for data engineering and analytics use cases. This paper provides a brief overview of Spark’s strengths and weaknesses in the context of data science and machine learning workflows.
Learn 4 milestones of digital transformation for health and life sciences organizations, 6 common challenges to reaching those milestones, and best practices that high-performing research and data science teams have adopted for dismantling these challenges.
Our missions are some of the most important and challenging in the world…from protecting our citizens to advancing the boundaries of science. The team from Lockheed Martin will talk about how Domino and NVIDIA have enabled engineers to streamline the build and deployment of machine learning capabilities…from AI competitions such...
Watch this webinar, hosted by Domino's Samit Thange and Bob Laurent, to learn more about the factors that can cause model performance to decrease, as well as some of the leading indicators to predict when it's time to re-train or re-build a model.
Join this webinar to experience new capabilities like on-demand Spark clusters, enhanced project management with Jira integration, ability to export models to Amazon SageMaker and Microsoft AKS certification first-hand via live demos and discussion.