Sciweavers

93 search results - page 12 / 19
» Evolving neural networks in compressed weight space
Sort
View
GECCO
2007
Springer
172views Optimization» more  GECCO 2007»
15 years 3 months ago
Acquiring evolvability through adaptive representations
Adaptive representations allow evolution to explore the space of phenotypes by choosing the most suitable set of genotypic parameters. Although such an approach is believed to be ...
Joseph Reisinger, Risto Miikkulainen
ECAL
2007
Springer
15 years 3 months ago
Neural Uncertainty and Sensorimotor Robustness
Real organisms live in a world full of uncertain situations and have evolved cognitive mechanisms to cope with problems based on actions and perceptions which are not always reliab...
Jose A. Fernandez-Leon, Ezequiel A. Di Paolo
IJCNN
2008
IEEE
15 years 4 months ago
Neuro-visual control in the Quake II game engine
— The first-person-shooter Quake II is used as a platform to test neuro-visual control and retina input layouts. Agents are trained to shoot a moving enemy as quickly as possibl...
Matt Parker, Bobby D. Bryant
NC
1998
140views Neural Networks» more  NC 1998»
14 years 11 months ago
Recurrent Neural Networks with Iterated Function Systems Dynamics
We suggest a recurrent neural network (RNN) model with a recurrent part corresponding to iterative function systems (IFS) introduced by Barnsley 1] as a fractal image compression ...
Peter Tiño, Georg Dorffner
ICASSP
2009
IEEE
15 years 4 months ago
Space Kernel Analysis
In this paper, we propose a novel nonparametric modeling technique, namely Space Kernel Analysis (SKA), as a result of the definition of the space kernel. We analyze the uncertai...
Liuling Gong, Dan Schonfeld