Sciweavers

599 search results - page 10 / 120
» Nonlinear dynamics in neural computation
Sort
View
NECO
2002
104views more  NECO 2002»
13 years 7 months ago
An Unsupervised Ensemble Learning Method for Nonlinear Dynamic State-Space Models
A Bayesian ensemble learning method is introduced for unsupervised extraction of dynamic processes from noisy data. The data are assumed to be generated by an unknown nonlinear ma...
Harri Valpola, Juha Karhunen
GECCO
2005
Springer
204views Optimization» more  GECCO 2005»
14 years 27 days ago
Modeling systems with internal state using evolino
Existing Recurrent Neural Networks (RNNs) are limited in their ability to model dynamical systems with nonlinearities and hidden internal states. Here we use our general framework...
Daan Wierstra, Faustino J. Gomez, Jürgen Schm...
ESANN
2004
13 years 8 months ago
Dynamic functional-link neural networks genetically evolved applied to system identification
: The contribution concerns the design of a generalised functional-link neural network with internal dynamics and its applicability to system identification by means of multi-input...
Teodor Marcu, Birgit Köppen-Seliger
JUCS
2007
107views more  JUCS 2007»
13 years 7 months ago
Genetic Algorithm Based Recurrent Fuzzy Neural Network Modeling of Chemical Processes
: A genetic algorithm (GA) based recurrent fuzzy neural network modeling method for dynamic nonlinear chemical process is presented. The dynamic recurrent fuzzy neural network (RFN...
Jili Tao, Ning Wang, Xuejun Wang
GECCO
2007
Springer
178views Optimization» more  GECCO 2007»
14 years 1 months ago
Nonlinear dynamics modelling for controller evolution
The problem of how to acquire a model of a physical robot, which is fit for evolution of controllers that can subsequently be used to control that robot, is considered in the con...
Julian Togelius, Renzo De Nardi, Hugo Gravato Marq...