Reservoir Computing is a new paradigm for using Recurrent Neural Networks which shows promising results. However, as the recurrent part is created randomly, it typically needs to b...
Xavier Dutoit, Benjamin Schrauwen, Jan M. Van Camp...
The broadcast nature of wireless networks is the source of both their utility and much of their complexity. To turn what would otherwise be unwanted interference into an advantage...
Mikhail Afanasyev, David G. Andersen, Alex C. Snoe...
Abstract-- Networks-on-Chip will serve as the central integration platform in future complex SoC designs, composed of a large number of heterogeneous processing resources. Most res...
— In this paper, we focus on the problem of designing an energy efficient MAC protocol for wireless sensor networks and propose a novel scheme, named as TEEM (Traffic aware, Ener...
A new class of data structures called "bumptrees" is described. These structures are useful for efficiently implementing a number of neural network related operations. A...