We propose a novel algorithm for extracting the structure of a Bayesian network from a dataset. Our approach is based on generalized conditional entropies, a parametric family of e...
Abstract. We present the Tom language that extends Java with the purpose of providing high level constructs inspired by the rewriting community. Tom bridges thus the gap between a ...
Horatiu Cirstea, Pierre-Etienne Moreau, Antoine Re...
The purpose of this work is to develop a pattern recognition system simulating the human vision. A transparent neural network, with context returns is used. The context returns co...
In this paper, we propose a software architecture model for the development of elaboration/transcoding modules for structured data. We define a flexible implementation approach ...
Current techniques for prefetching linked data structures (LDS) exploit the work available in one loop iteration or recursive call to overlap pointer chasing latency. Jumppointers...