Back

Speaker "Chris Fregly" Details Back

 

Topic

Building Continuous ML/AI Pipelines with TFX, KubeFlow, Airflow, and MLflow

Abstract

In this talk, I build a real-world machine learning pipeline using TensorFlow Extended (TFX), KubeFlow, Airflow, and MLflow.
 
Described in a 2017 paper from Google, TFX is used internally by thousands of Google data scientists and engineers across every major product line within Google.
 
KubeFlow is a modern, end-to-end pipeline orchestration framework that embraces the latest AI best practices including hyper-parameter tuning, distributed model training, and
model tracking.
 
Airflow is the most-widely used pipeline orchestration framework in machine learning and data engineering.
 
MLflow is a lightweight experiment-tracking system recently open-sourced by Databricks, the creators of Apache Spark. MLflow supports Python, Java/Scala, and R - and offers native support for TensorFlow, Keras, and Scikit-Learn.
 
Attendees will come away with a better understanding of the tools needed for a modern, iterative ML/AI pipeline.

Profile

Chris Fregly is Founder and Research Engineer at PipelineAI (http://pipeline.ai), a real-time Machine Learning and Artificial Intelligence Startup based in San Francisco.  

He is also an Apache Spark Contributor, a Netflix Open Source Committer, founder of the Global Advanced Spark and TensorFlow Meetup, author of the O’Reilly Training and Video Series titled, "High Performance TensorFlow in Production."

Previously, Chris was a Distributed Systems Engineer at Netflix, a Data Solutions Engineer at Databricks, and a Founding Member and Principal Engineer at the IBM Spark Technology Center in San Francisco.