The Predictive Linear Gaussian model (or PLG) improves upon traditional linear dynamical system models by using a predictive representation of state, which makes consistent parame...
This paper presents an algorithm for extract ing propositions from trained neural networks. The algorithm is a decompositional approach which can be applied to any neural networ...
The study of Joint Source-Channel Coding (JSCC) systems faces one major challenge in obtaining an analytical expression for the function that links end-to-end distortion with chann...
Abstract--This paper presents a new approach to soft demodulation for MIMO channels. The proposed method is an approximation to the exact a posteriori probability-per-bit computer....
We introduce a family of box splines for efficient, accurate and smooth reconstruction of volumetric data sampled on the Body Centered Cubic (BCC) lattice, which is the favorable v...
Alireza Entezari, Dimitri Van De Ville, Torsten M&...