Fernando Silva

Learn More
We propose and evaluate a novel approach called On-line Distributed NeuroEvolution of Augmenting Topologies (odNEAT). odNEAT is a completely distributed evolutionary algorithm for online learning in groups of embodied agents such as robots. While previous approaches to online distributed evolution of neural controllers have been limited to the optimisation(More)
We propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. We combine online evolution of weights and network topology with neuromodulated learning. We demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic concurrent foraging task. In(More)
Several solutions have been proposed to provide authentication and safe encryption for Wifi networks in order to overcome the limitation of WEP based security. This document describes a solution based on IPSec VPNs with client and server certificates. The key advantages of this solution is its ability to provide roaming between institutions without having(More)
INTRODUCTION Primary intracardiac tumors are rare and approximately 50% are myxomas. The majority of myxomas are located in the left atrium and have variable clinical presentation. We report a case of a large myxoma in the right atrium, which is an uncommon location for this type of tumor. CASE PRESENTATION A 45-year-old Caucasian woman with a history of(More)
The authors propose and evaluate a novel approach to the online synthesis of neural controllers for autonomous robots. The authors combine online evolution of weights and network topology with neuromodulated learning. The authors demonstrate our method through a series of simulation-based experiments in which an e-puck-like robot must perform a dynamic(More)
Swarm robotics is a promising approach for the coordination of large numbers of robots. While previous studies have shown that evolutionary robotics techniques can be applied to obtain robust and efficient self-organized behaviors for robot swarms, most studies have been conducted in simulation, and the few that have been conducted on real robots have been(More)
Online evolution gives robots the capacity to learn new tasks and to adapt to changing environmental conditions during task execution. Previous approaches to online evolution of neural controllers are typically limited to the optimisation of weights in networks with a prespecified, fixed topology. In this article, we propose a novel approach to online(More)
Neuroevolution, the optimisation of artificial neural networks (ANNs) through evolutionary computation, is a promising approach to the synthesis of controllers for autonomous agents. Traditional neuroevolution approaches employ direct encodings, which are limited in their ability to evolve complex or large-scale controllers because each ANN parameter is(More)