Sciweavers

401 search results - page 24 / 81
» Evolving a neural network using dyadic connections
Sort
View
TNN
1998
114views more  TNN 1998»
13 years 7 months ago
A new approach to artificial neural networks
: A novel approach to artificial neural networks is presented. The philosophy of this approach is based on two aspects: the design of task-specific networks, and a new neuron model...
Benedito Dias Baptista F. Filho, Eduardo Lobo Lust...
ICANN
2007
Springer
13 years 11 months ago
Text-Independent Speaker Authentication with Spiking Neural Networks
This paper presents a novel system that performs text-independent speaker authentication using new spiking neural network (SNN) architectures. Each speaker is represented by a set ...
Simei Gomes Wysoski, Lubica Benuskova, Nikola Kasa...
EVOW
2008
Springer
13 years 9 months ago
Implicit Fitness Functions for Evolving a Drawing Robot
We describe an approach to artificially evolving a drawing robot using implicit fitness functions, which are designed to minimise any direct reference to the line patterns made by ...
Jon Bird, Phil Husbands, Martin Perris, Bill Bigge...
GECCO
2008
Springer
179views Optimization» more  GECCO 2008»
13 years 8 months ago
Developing neural structure of two agents that play checkers using cartesian genetic programming
A developmental model of neural network is presented and evaluated in the game of Checkers. The network is developed using cartesian genetic programs (CGP) as genotypes. Two agent...
Gul Muhammad Khan, Julian Francis Miller, David M....
EH
2005
IEEE
158views Hardware» more  EH 2005»
14 years 1 months ago
Hardware Evolution of Analog Circuits for In-situ Robotic Fault-Recovery
We present a method for evolving and implementing artificial neural networks (ANNs) on Field Programmable Analog Arrays (FPAAs). These FPAAs offer the small size and low power usa...
Dmitry Berenson, Nicolás S. Estévez,...