Abstract—In this work we present a variational formulation for a multilayer perceptron neural network. With this formulation any learning task for the neural network is defined ...
Explaining policies of Markov Decision Processes (MDPs) is complicated due to their probabilistic and sequential nature. We present a technique to explain policies for factored MD...
We study a maximum flow problem in a polygonal domain P: Determine the maximum number of disjoint "thick" paths (of specified width w) through P from a source edge to a ...
A stent device is a permanent metallic implant currently used to prop open arteries blocked with atherosclerotic plaques. Many classes of stents are available and mainly differ b...
We present a simple and effective approach to complement search results for children's web queries with child-oriented multimedia results, such as coloring pages and music sh...