Explore a groundbreaking approach to ML platforms that goes beyond the traditional "Kaggle Paradigm" in this 24-minute conference talk by Norm Zhou, Founding Engineer at a Stealth Startup. Discover how a policy-centric view can revolutionize ML system building and increase engineering productivity. Learn about two major additions to the model-centric approach: a fully managed unified data collection system and downstream extension to A/B testing systems. Understand how these innovations enable end-to-end automation, directly improving business metrics and addressing changing business needs more effectively. Gain insights into the limitations of current ML system building approaches and explore a new paradigm that promises to enhance intelligent data-driven applications with limited engineering effort.
ML Platform Beyond Kaggle Paradigm - Policy-Centric Approach for End-to-End Automation
MLOps World: Machine Learning in Production via YouTube
Overview
Syllabus
ML Platform Beyond Kaggle Paradigm
Taught by
MLOps World: Machine Learning in Production
Related Courses
-
Avoid ML OOps with ML Ops - A Modular Approach to Scaling End-to-End ML Platforms
-
MLOps Platform Architecture for End-to-End ML Pipelines
-
Fully Automated ML Platform Using Kubeflow and Declarative Approach to End-to-End ML Development
-
State of the Industry - Machine Learning Platforms and MLOps
-
Interpretable Machine Learning Use-Cases - Kaggle 30 Days of ML Day 15
