Delivering Innovative Health with Generative AI Solutions at Merck

In this video, learn how Merck uses Amazon Web Services (AWS) to solve a common problem in the pharmaceutical industry—the occurrence of false rejects. Merck’s goal is to get life-saving drugs into customers’ hands faster and in a safe manner. It ingests real-time data from various manufacturing processes and inspection machines, and then contextualizes and harmonizes the data. Merck uses AWS Glue and Amazon Kinesis to ingest, transform, and contextualize near real-time data, run analytics on that data and load the harmonized data into Amazon Redshift, which is then used by its analytics dashboards including Amazon QuickSight. Merck’s artificial intelligence and machine learning (AI/ML) platform is built on Amazon SageMaker and uses AWS DataSync to ingest defect image data from inspection machines across sites. Merck uses generative AI approaches and generative models such as Generative Adversarial Networks (GANs) and Variational Autoencoders to develop synthetic defect image data for complex defects where it has limited training data.