Re:A grand unified theory of AI
by stochastician on Tuesday March 30, 2010 @08:05PM
(#1230550)
The idea here is using "Stochastic Functional Programming" (see some of the work by Goodman, Mansinghka, Roy, and others at http://web.mit.edu/vkm/www/ ). Basically, you write down your AI problem in a "forward" direction, suggesting how the data came to be. You then "fix" the outputs. The engine generates a distribution on "possible program histories" that preserves the statistical properties you care about.
For people familiar with inverse methods, what they basically have here is a generalized inverse solving engine that obeys the laws of probability.
Of course, right now, this approach ("solving AI by running programs backwards") is a bit slow, but some startups are rethinking the entire computing stack ( http://www.naviasystems.com ) in an attempt to rectify that. [I'm one of the people at said company]
For people familiar with inverse methods, what they basically have here is a generalized inverse solving engine that obeys the laws of probability.
Of course, right now, this approach ("solving AI by running programs backwards") is a bit slow, but some startups are rethinking the entire computing stack ( http://www.naviasystems.com ) in an attempt to rectify that. [I'm one of the people at said company]