no code implementations • 2 Feb 2018 • Michael Harradon, Jeff Druce, Brian Ruttenberg
We develop an approach to explaining deep neural networks by constructing causal models on salient concepts contained in a CNN.
no code implementations • 27 Apr 2017 • Avi Pfeffer, Brian Ruttenberg, Lee Kellogg, Michael Howard, Catherine Call, Alison O'Connor, Glenn Takata, Scott Neal Reilly, Terry Patten, Jason Taylor, Robert Hall, Arun Lakhotia, Craig Miles, Dan Scofield, Jared Frank
Artificial intelligence methods have often been applied to perform specific functions or tasks in the cyber-defense realm.
no code implementations • 10 Jun 2016 • Avi Pfeffer, Brian Ruttenberg, William Kretschmer
Reasoning on large and complex real-world models is a computationally difficult task, yet one that is required for effective use of many AI applications.
no code implementations • 11 Sep 2015 • Avi Pfeffer, Brian Ruttenberg, Amy Sliva, Michael Howard, Glenn Takata
In this paper, we present a new inference framework, lazy factored inference (LFI), that enables factored algorithms to be used for models with infinitely many variables.