Sciweavers

727 search results - page 20 / 146
» A theoretical framework for multiple neural network systems
Sort
View
ESANN
2008
13 years 10 months ago
A Regularized Learning Method for Neural Networks Based on Sensitivity Analysis
The Sensitivity-Based Linear Learning Method (SBLLM) is a learning method for two-layer feedforward neural networks, based on sensitivity analysis, that calculates the weights by s...
Bertha Guijarro-Berdiñas, Oscar Fontenla-Ro...
ECAL
2007
Springer
14 years 23 days ago
Genotype Reuse More Important than Genotype Size in Evolvability of Embodied Neural Networks
odel of Embodiment on Abstract Systems: from Hierarchy to Heterarchy Kohei Nakajima, Soya Shinkai, Takashi Ikegami A Behavior-Based Model of the Hydra, Phylum Cnidaria Malin Aktius...
Chad W. Seys, Randall D. Beer
TNN
2008
106views more  TNN 2008»
13 years 8 months ago
Stability and Hopf Bifurcation of a General Delayed Recurrent Neural Network
In this paper, stability and bifurcation of a general recurrent neural network with multiple time delays is considered, where all the variables of the network can be regarded as bi...
Wenwu Yu, Jinde Cao, Guanrong Chen
IROS
2007
IEEE
126views Robotics» more  IROS 2007»
14 years 3 months ago
A graph theoretic approach to optimal target tracking for mobile robot teams
Abstract— In this paper, we present an optimization framework for target tracking with mobile robot teams. The target tracking problem is modeled as a generic semidefinite progr...
Jason C. Derenick, John R. Spletzer, M. Ani Hsieh
ECAL
2007
Springer
14 years 3 months ago
Measuring Entropy in Embodied Neural Agents with Homeostasic Units: A Link Between Complexity and Cybernetics
Abstract. We present a model of a recurrent neural network with homeostasic units, embodied in a minimalist articulated agent with a single link and joint. The configuration of th...
Jorge Simão