Sciweavers

4 search results - page 1 / 1
» Evolving modular neural-networks through exaptation
Sort
View
CEC
2009
IEEE
13 years 10 months ago
Evolving modular neural-networks through exaptation
— Despite their success as optimization methods, evolutionary algorithms face many difficulties to design artifacts with complex structures. According to paleontologists, living...
Jean-Baptiste Mouret, Stéphane Doncieux
ANNS
2010
12 years 10 months ago
Search Space Restriction of Neuro-evolution through Constrained Modularization of Neural Networks
Evolving recurrent neural networks for behavior control of robots equipped with larger sets of sensors and actuators is difficult due to the large search spaces that come with the ...
Christian W. Rempis, Frank Pasemann
PPSN
2004
Springer
13 years 9 months ago
A Neuroevolutionary Approach to Emergent Task Decomposition
A scalable architecture to facilitate emergent (self-organized) task decomposition using neural networks and evolutionary algorithms is presented. Various control system architectu...
Jekanthan Thangavelautham, Gabriele M. T. D'Eleute...
GLVLSI
1998
IEEE
124views VLSI» more  GLVLSI 1998»
13 years 8 months ago
Non-Refreshing Analog Neural Storage Tailored for On-Chip Learning
In this research, we devised a new simple technique for statically holding analog weights, which does not require periodic refreshing. It further contains a mechanism to locally u...
Bassem A. Alhalabi, Qutaibah M. Malluhi, Rafic A. ...