Learning piecewise control strategies in a modular neural network architecture
The authors describe a multinetwork, or modular, neural network architecture that learns to
perform control tasks using a piecewise control strategy. The architecture's networks …
perform control tasks using a piecewise control strategy. The architecture's networks …
Recognition of manipulated objects by motor learning with modular architecture networks
For recognition and control of multiple manipulated objects, we present two learning
schemes for neuralnetwork controllers based on feedback-error-learning and modular …
schemes for neuralnetwork controllers based on feedback-error-learning and modular …
Mobile robot control by a structured hierarchical neural network
S Nagata, M Sekiguchi… - IEEE Control Systems …, 1990 - ieeexplore.ieee.org
A mobile robot whose behavior is controlled by a structured hierarchical neural network and
its learning algorithm is presented. The robot has four wheels and moves about freely with …
its learning algorithm is presented. The robot has four wheels and moves about freely with …
Neural network application for direct feedback controllers
Y Ichikawa, T Sawa - IEEE Transactions on neural networks, 1992 - ieeexplore.ieee.org
The author presents a learning algorithm and capabilities of perceptron-like neural networks
whose outputs and inputs are directly connected to plants just like ordinary feedback …
whose outputs and inputs are directly connected to plants just like ordinary feedback …
Challenging control problems
CW Anderson, WT Miller - Neural networks for control, 1990 - direct.mit.edu
In this appendix, we present a number of control problems as challenges to experimenters
wishing to explore new ideas for building automatic controllers that improve their …
wishing to explore new ideas for building automatic controllers that improve their …
A multilayered neural network controller
D Psaltis, A Sideris… - IEEE control systems …, 1988 - ieeexplore.ieee.org
A multilayered neural network processor is used to control a given plant. Several learning
architectures are proposed for training the neural controller to provide the appropriate inputs …
architectures are proposed for training the neural controller to provide the appropriate inputs …
[PDF][PDF] Neural networks in feedback control systems
Dynamical systems are ubiquitous in nature and include naturally occurring systems such as
the cell and more complex biological organisms, the interactions of populations, and so on …
the cell and more complex biological organisms, the interactions of populations, and so on …
Real-time application of neural networks for sensor-based control of robots with vision
WT Miller - IEEE Transactions on Systems, Man, and …, 1989 - ieeexplore.ieee.org
A practical neural network-based learning control system is described that is applicable to
complex robotic systems involving multiple feedback sensors and multiple command …
complex robotic systems involving multiple feedback sensors and multiple command …
The functional link net and learning optimal control
YH Pao, SM Phillips - Neurocomputing, 1995 - Elsevier
We present a strategy for learning optimal control. The approach uses functional-link neural
network implementations which have several beneficial properties giving advantages over …
network implementations which have several beneficial properties giving advantages over …
Neural network architecture for control
Two important computational features of neural networks are associative storage and
retrieval of knowledge, and uniform rate of convergence of network dynamics independent …
retrieval of knowledge, and uniform rate of convergence of network dynamics independent …