The Fifth Elephant 2019

In this talk we will explain how TransmogrifAI - AutoML library on top of Apache spark helps build automated machine learning pipelines with features engineering, feature selection. It provides Automatic Model selection along with automated model hyper parameter tuning.

Outline

• Introduction
• Need of Multicloud and multi tenant models
• Lessons learned while building Einstein platform
• How traditional machine learning works
• Introducing TransmogrifAI
• Type Hierarchy
• Automatic Feature Engineering across text, categorical, numerical, spatial features
• Handling label leakage
• Autmatic Model Selection and hyper parameter tuning
• Models supported currently
• Demo
• Uses cases being solved in production
• Summary

Requirements

Familiarity with ML, Scala and Spark is good to have, but is not necessary to attend this tutorial.

The following requirements must be fulfilled before attending this tutorial:

1. Laptop with 8GB RAM is a must.
2. Ubuntu and Mac OS are suitable for this workshop.
3. Install latest version of docker (version 18.0 or above)
4. Run this command: docker pull beakerx/beakerx

Speaker bio

Rajdeep is leading Industries Einstein team at Salesforce which is leveraging TransmogirfAI based data pipeline to solve ML problems across domains. He has overall 19 years of Software experience and has written 3 books in area on ML and DL.

Links

• https://docs.transmogrif.ai/en/stable/

Slides

https://docs.google.com/presentation/d/1mnXEqmlVEFpr5xBkXWh-PalP9ZUdstXXAemCfwgqaYw/edit?usp=sharing