Last modified 7 weeks ago Last modified on 03/10/17 17:03:17

Probabilistic Programming for Advancing Machine Learning Picture by Matt Buck

Machine Learning is at the heart of modern approaches to artificial intelligence. The field posits that teaching computers how to learn can be significantly more effective than programming them explicitly. Unfortunately, building effective machine learning applications currently still requires Herculean efforts on the part of highly trained experts in machine learning.

Probabilistic Programming is a new programming paradigm for managing uncertain information. The goal of the Probabilistic Programming for Advancing Machine Learning (PPAML) program is to facilitate the construction of machine learning applications by using probabilistic programming to:

  1. Dramatically increase the number of people who can successfully build machine learning applications;
  2. Make machine learning experts radically more effective; and
  3. Enable new applications that are inconceivable today.

The PPAML program started in November 2013 and is scheduled to run 46 months, with three phases of activity through 2017.

About PPAML Challenge Problem Descriptions
Program Overview #1. Quad-Rotor Sensor Fusion
Announcements #2. Continent-Scale Bird Migration Modeling
Summer Schools #3. Wide Area Motion Imagery Track Linking
Milestones #4. Small Problems Collection
Presentations #5. Natural Language Processing
Resources #6. Image Labeling
Press #7. Flu Spread
#8. Desktop Activity Recognition
#9. Gapminder Data Analysis
Problem #10 2017 July

Modified Fri Mar 10 17:03:17 2017 by Eric.Woldridge.