Center

The AI Model Share Project

The AI Model Share Project is a newly funded academic center at Columbia University. Its mission is to generate the tools needed to assist students, faculty, and the wider data science community to bring machine learning innovations to all manner of end-users. The initiative received Start Up Center grant funding from ISERP in July of 2019 to build a platform (Python library + integrated website) that will act as the world's trusted academic repository for machine learning model prediction APIs. To date we have used these resources to rapidly generate the core functionality of this platform.

The platform now enables faculty, students, and the wider data science community to launch machine learning models into scalable production ready prediction REST APIs using a single Python function. Details about each model, how to use the model's API, and the model's author(s) are deployed simultaneously into a searchable website at Columbia. Data scientists (faculty, students and otherwise) have individual model detail pages listing information about all deployed models. Each of these pages includes a fully functional prediction dashboard that allows end-users to input text, tabular, or image data and receive live predictions. Moreover, documentation for prediction API usage via Curl, Python, and R code are also available.

In a matter of seconds, data scientists can launch a model into this infrastructure and end-users the world over will be able to engage their machine learning models. A developer version of the platform is currently being used by Columbia students, faculty, and staff to test and improve platform functionality through the spring semester of 2020. The site will be publicly launched in summer 2020. With this foundation in place, we will continue to contribute innovate, but practically useful value-added tools into the machine learning model building workflow such as collaborative team oriented model building and model meta-data tracking functionality.

Director(s): 

Michael Parrott

Lecturer in the Discipline of Political Science

Newsletter

Don't want to miss our interesting news and updates! Make sure to join our newsletter list.

* indicates required

Contact us

For general questions about ISERP programs, services, and events.