IBM Big Data & AI Chicago: Open standards for Machine Learning pipeline deployment

Chicago

September 18, 2020 6:30 pm EST

This is a joint event with an amazing Washington, DC – based group Deep Learning Adventures (https://www.meetup.com/Deep-Learning-Adventures).

Join Zoom Meeting:
https://us02web.zoom.us/j/84402592502?pwd=d1lVSkxQZE1sSGljR3dXaEZwYmNEdz09

Phone: +1 929 205 6099 US
Meeting ID: 844 0259 2502

Agenda:
– Introductions and get to know our community

– Join Deep Learning Adventures on Slack:
https://join.slack.com/t/deeplearninga-nmk8930/shared_invite/zt-gpqxpg6u-U7TRpIRE3NgsAum6BC2IZQ

 

Deep Learning YouTube playlists, feel free to share and subscribe 😀
Our introductory level adventures in TensorFlow are available at https://bit.ly/deep–learning-tf
Our advanced coding sessions in TensorFlow are available at https://bit.ly/deep-learning-tf-coding
Our guest speaker sessions are available at
https://bit.ly/deep-learning-tf-speakers

The main presentation:
Machine Learning (ML) model/pipeline exchange and deployment has long been a bottleneck in the traditional ML lifecycle implementation for an enterprise. The ability to develop a model or pipeline in one system and then deploy it to a different one is very difficult to find, in most cases either the same system has to be used or an expensive and error-prone recoding is required. Predictive Model Markup Language (PMML) and Portable Format for Analytics (PFA) developed by the Data Mining Group (DMG) helped to alleviate this problem for traditional ML models and pipelines, but did not address deep learning. In 2017 Microsoft and Facebook open-sourced “Open Neural Network Exchange (ONNX)”, a new open format for both deep learning and traditional ML. Its popularity has grown tremendously since then. In this talk we will discuss the open standards and related open source projects, as well as their applications and ways to contribute.

 

– Links
PMML: http://dmg.org/pmml/v4-4-1/GeneralStructure.html
PFA: http://dmg.org/pfa/index.html
ONNX: http://onnx.ai

About the speaker
Svetlana Levitan (https://www.linkedin.com/in/svetlanalevitan) has been a software engineer and technical lead for IBM SPSS statistical and machine learning components for many years and a Senior Developer Advocate with IBM Center for Open Source Data and Artificial Intelligence Technologies. Svetlana represented SPSS and IBM at the Data Mining Group (DMG), working with representatives from other companies on PMML, a popular open standard for model deployment. Lately she also works on another open standard, ONNX, that is quickly gaining popularity in Deep Learning communities. Svetlana is a co-organizer of several Chicago meetup groups and a conference presenter. She holds a PhD in Applied Mathematics and MS in Computer Science from University of Maryland, College Park. Svetlana loves to learn new technologies and to share her expertise and takes every opportunity to involve girls into STEM. Currently she is a volunteer Senior Data Scientist with a small startup and is looking for a full-time Data Scientist position in the Chicago area or remote.

Chicago, United States

Legend