Scalable Optimization of Large Systems with MLOps
Despite the promising outcomes from the proof-of-concept phase, a significant number of machine learning projects terminate prematurely, failing to make the transition to production.In this talk we show how a three step MLOps strategy helps to determine what needs to be done to lift and shift a prototype to the Microsoft Azure cloud.
We address the challenges of introducing MLOps for controlling and optimizing hundreds of industrial air separation plants using a model-based deep reinforcement learning methodology, emphasising the need for parametrization, scalability, and manageability while also taking architecture considerations into account.
Vorkenntnisse
- Basic knowledge of machine learning, data management, and MLOps.
Lernziele
Understanding the decision-making factors for implementing MLOps for large systems in the cloud, including data management, data pipeline, ML pipeline, evaluation, and serving.
Speaker
Shreya Bhatia holds a Masters in Chemical Engineering. At Linde GmbH she works on bridging the gap between the chemical process industry and software development. With 4+ years of experience at Linde, she developed data-based tools for optimizing plant operations. These tools enable real-time monitoring of equipment and effective control of small and large-scale systems.
Melanie B. Sigl is a Managing Consultant, leading the Machine Learning department at PRODATO Integration Technology GmbH and supports customers in their data integration projects using Machine Learning. She leverages proven practices from software development, software engineering, and MLOps to ensure the successful implementation of AI projects.
M3-Newsletter
Du möchtest über die Minds Mastering Machines
auf dem Laufenden gehalten werden?