What we're about

Chicago ML is a community of machine learning researchers and engineers in the greater Chicago area. Learn more at https://chicago.ml.

If you're new to machine learning or a seasoned veteran, there are opportunities for you to grow in this community! Consider attending an upcoming meetup, or if you have a topic that you'd like to share with others, consider presenting - there's no experience needed, just your enthusiasm and a topic you think is interesting.

The best way to contact us is through the Chicago ML Slack channel. Signup at http://bit.ly/chicago-ml-slack (https://bit.ly/2S0zFAP) and post a topic suggestion in the #presentations channel. We'll be happy to work with your schedule to find a meetup for you to present!

Our Pledge

In the interest of fostering an open and welcoming environment, we pledge to making participation in our project and our community a harassment-free experience for everyone, regardless of age, body size, disability, ethnicity, gender identity and expression, level of experience, nationality, personal appearance, race, religion, or sexual identity and orientation.

For our complete code of conduct, see https://chicago.ml/conduct/ .

Upcoming events (1)

Model deployment with DRUM

Online event

Rajiv and Tim will provide a short overview of typical model deployment patterns and then focus on a new open-source package, DRUM, for model deployment. The talk will walk through how to go from a python scikit model, get REST API endpoint, test it for common deployment issues, and deploy it. This is performed using a new open-source package, DRUM, that can helps you move beyond flask and take advantage of NGINX and uWSGI for serving models anywhere in a production-grade manner. This package provides built-in support for a variety of modeling frameworks including Keras, scikit learn, R, H2O, DataRobot, and more. To make deployment easier, DRUM also incorporates unit testing for common deployment issues. All of this is easy to containerize and even add monitoring agents. The result is a simplified workflow that is attuned to the needs of machine learning deployment. Tim Whittaker is a Data scientist with DataRobot, where his primary focus is on customer success. Tim is passionate about MLOps and is a contributor to DataRobot’s open source model deployment package DRUM. Rajiv Shah is a data scientist a DataRobot, where his primary focus is on helping customers achieve success with AI. He has published research papers, spoken at conferences, and received patents in many domains including sports analytics, deep learning, and interpretability. He also enjoys mentoring data scientists, and participating at meetups. Before DataRobot, Rajiv was a part of data science teams at Caterpillar and State Farm and received a Ph.D. from the University of Illinois at Urbana Champaign.

Past events (45)

Photos (84)