Probabilistic Programming with Scala

Full title: Democratizing Machine Learning and Artificial Intelligence: Probabilistic Programming with Scala

Speaker: Brian Ruttenberg

Abstract:

Probabilistic models form the foundation of modern ML and AI. However, building and using models that represent large and complex scenarios is a daunting task for even the most expert and experienced programmers. As a result, there has been significant effort lately on the development of probabilistic programming languages, enabling probabilistic processes and algorithms to be specified using programming language constructs. These languages allow users to quickly and easily construct probabilistic models with little ML and AI experience.

In this talk, I will discuss Figaro, an open source, Scala-based probabilistic programming language. I will focus mostly on how to use the language, how it is integrated with Scala, why we chose Scala as the base language, and present some examples of what one can do with Figaro. Experience in ML and AI should not be necessary to follow the talk.

hangout afterwards at Catalyst (300 Technology Square, by Main & Albany)

At MIT, allow extra time to find the room. Enter the Stata Center at 32 Vassar Street, opposite the sign for 43 Vassar Street. Take the elevator (under a sign saying "Alexander W Dreyfoos Building" to the fourth floor. (If you find yourself instead in the Gates Building part of the Stata Center, walk to the other end of the buildling to the Dreyfoos elevators). On the fourth floor, turn left out of the elevator and then right, through double doors, straight onto orange carpet, then right.

(building doors locked? wait a few minutes for someone to go in or out)