ML Model Deployment and Scoring on the Edge with Automatic ML & DF / Flink2Kafka
This video was recorded on June 18, 2020.
Slides from the presentation are available here: https://www.slideshare.net/0xdata/ml-...
OUTLINE:
0:00 - Start
0:06 - Meetup Welcome
0:33 - ML Model Deployment and Scoring Overview & Challenges
18:48 - Cloudera Data Flow Platform for Mojo Deployment
20:30 - Mojo Deployment to Apache NiFi Demo
35:56 - Resources for Mojo Deployment to NiFi & MiNiFi C++
36:20 - H2O.ai Learning Center
37:26 - Questions on Mojo Deployment
47:45 - Transition to Apache Flink
48:19 - Apache Flink & Kafka Overview
52:00 - Demo Reference Architecture (NiFi, Kafka, Flink)
1:04:05 - Additional Documentation for Demo
1:04:32 - Questions & Discussion (Real-Time Streaming ML, etc)
1:26:15 - Closing
Machine Learning Model Deployment and Scoring on the Edge with Automatic Machine Learning and Data Flow
Deploying Machine Learning models to the edge can present significant ML/IoT challenges centered around the need for low latency and accurate scoring on minimal resource environments. H2O.ai's Driverless AI AutoML and Cloudera Data Flow work nicely together to solve this challenge. Driverless AI automates the building of accurate Machine Learning models, which are deployed as light footprint and low latency Java or C++ artifacts, also known as a MOJO (Model Optimized). And Cloudera Data Flow leverage Apache NiFi that offers an innovative data flow framework to host MOJOs to make predictions on data moving on the edge.
Speakers:
James Medel (H2O.ai - Technical Community Maker)
Greg Keys (H2O.ai - Solution Engineer)
Kafka 2 Flink - An Apache Love Story
This project has heavily inspired by two existing efforts from Data In Motion's FLaNK Stack and Data Artisan's blog on stateful streaming applications. The goal of this project is to provide insight into connecting an Apache Flink applications to Apache Kafka.
Speaker:
Ian R Brooks, PhD (Cloudera - Senior Solutions Engineer & Data)
For the presentation slides, you can also download them at this H2O Training link: https://training.h2o.ai/products/ml-m...
Driverless AI Mojo Deployment Examples GitHub Links:
https://github.com/james94/dai-deploy...
Flink2Kafka GitHub Links:
https://github.com/BrooksIan/Flink2Kafka