Ensemble neural networks
T. Baidyk, Ernst Kussul
- Year
- 2009
- Citations
- 5
Abstract
This paper contains brief description of ensemble neuron networks and some results of storage capacity estimation. Storage capacity shows how many ensembles can be stored in the neuron network of given size (given number of neurons in the network). It is shown that the number of ensembles can be much larger than the number of neurons in the network. We propose to apply this ensemble neural network to the problem of selection of adequate maneuver for robot-manipulator. At the input of the ensemble neural network we have the image of situation presented by the web-camera, and the output of the network will present us appropriate maneuver. The ensemble neural network is a good formalism for different maneuver representations. We propose to use ensemble neuron networks for this purpose.
Keywords
Related papers
Statistical Learning Theory
Yuhai Wu, Vladimir Vapnik
1999
Artificial intelligence: a modern approach
1995
Applied Nonlinear Control
Jean-Jacques Slotine, Weiping Li
1991
A new optimizer using particle swarm theory
R.C. Eberhart, James Kennedy
2002