Learn how to effectively transition machine learning models from development to production in this conference talk from Data Science Conference Europe 2022. Discover the engineering perspective on collaborating with data science teams to ensure models are production-ready. Master a systematic checklist approach covering model purpose understanding, input/output definition, system integration timing, and hosting decisions. Gain insights into gathering model requirements, optimizing performance for production environments, and implementing engineering best practices that enhance data science workflows. Through practical examples, explore key considerations and methodologies for successfully deploying models as part of larger systems.
Overview
Syllabus
Engineers guide for shepherding models in to production | Marko Dimitrijevic | DSC Europe 2022
Taught by
Data Science Conference
Related Courses
-
MLOps1 (Azure): Deploying AI & ML Models in Production using Microsoft Azure Machine Learning
-
Developing Machine Learning Models for Production
-
Machine Learning Engineering for Production (MLOps)
-
Deploy Trained Models
-
Machine Learning in Production
-
Model Deployment and Maintenance for Data Scientists
