Rule extraction is a technique aimed at transforming highly accurate opaque models like neural networks into comprehensible models without losing accuracy. G-REX is a rule extract...
— In this paper, we propose a new supervised learning method whereby information is controlled by the associated cost in an intermediate layer, and in an output layer, errors bet...
Many processes are composed of a n-fold repetition of some simpler process. If the whole process can be modeled with a neural network, we present a method to derive a model of the...
The ability of communicating with a selected party anonymously is an important aspect of network security. Communicating anonymously means that no adversary can discern who is com...
—We present the design and implementation of a parallel exact inference algorithm on the Cell Broadband Engine (Cell BE). Exact inference is a key problem in exploring probabilis...