Algorithmia in Action: Take Your ML Models from Training to Production
Algorithmia is machine learning operations (MLOps) software that manages all stages of the ML lifecycle within existing operational processes. In this session, we’ll demonstrate Algorithmia in action and show you how it solves common challenges to deploy models, connect to data sources, automatically scale model inference, and manage the ML lifecycle in a centralized model catalog. Using an example use case, we'll demonstrate how to deploy a GPU-based deep learning model in Algorithmia, build a model serving pipeline, and monitor model performance metrics. We’ll also discuss how Algorithmia handles the underlying MLOps infrastructure and operations related to security, scalability, and governance.
Key Takeaways 1. Easily build and publish CPU- and GPU-based deep learning models 2. Chain different languages and algorithm types together in a single model serving pipeline 3. Instrument model performance metrics to monitor data drift and concept drift
Kristopher Overholt is a Sales and Solution Engineer at Algorithmia who works with machine learning operations, enterprise architecture, and data science workflows. He studied civil engineering at The University of Texas at Austin, where he completed his PhD in 2013. He has been working with enterprise customers for the last 6 years to help them move their data science and machine learning code into production.