What happens after you deploy a machine learning model? How do you make sure that your model performance doesnot degrade as data and the world change?
In this talk, Danny D. Leybzon will explain how monitoring ML models in production is key to deriving value from your machine learning initiatives.
The talk is meant to answer three main questions:
1. What is ML monitoring?
2. Why do we care about ML monitoring?
3. How do we monitor ML models?
It seamlessly intertwines both theory and practice, leaving attendees with an in-depth understanding of how to think about their machine learning models in production
Danny Leybzon (Imply)
Danny has worn many hats, all of them related to data. He studied computational statistics at UCLA, before becoming first an analyst and then a product manager at a big data platform named Qubole. Since then, he has worked to evangelize machine learning best practices, talking on subjects such as distributed deep learning, productionizing machine learning models, and automated machine learning.
When Danny is not researching, practicing, or talking about data science, he is usually doing one of his numerous outside hobbies: rock climbing, backcountry backpacking, skiing, etc.