Investigation of simply coded evolutionary artificial neural networks on robot control problems

2008 ◽  
Author(s):  
Yoshiaki Katada ◽  
Jun Nakazawa
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Robot Control ◽  
Control Problems ◽  
Artificial Neural

Artificial Neural Network for Solving the Inventory Control Problem in Fuzzy Environments

2021 ◽  
pp. 126-143
Author(s):  
Mostafijur Rahaman ◽  
Sankar Prasad Mondal ◽  
Shariful Alam
Keyword(s):  
Neural Network ◽  
Differential Equation ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Artificial Neural Networks ◽  
Inventory Control ◽  
Solution Procedure ◽  
Control Problems ◽  
Fuzzy Environment ◽  
Artificial Neural

In this chapter, different inventory control problems are formulated in fuzzy environment and solved by artificial neural network. Due to present the non-linearity associated with the differential equation in fuzzy environment, the solution procedure may be very complicated. To avoid the situation, artificial neural networks play an important role. In this chapter, different inventory control problems are formulated in fuzzy environment and solved by artificial neural network. Due to present the non-linearity associated with the differential equation in fuzzy environment, the solution procedure may be very complicated. To avoid the situation, artificial neural networks play an important role.

PRUNING ARTIFICIAL NEURAL NETWORKS USING NEURAL COMPLEXITY MEASURES

2008 ◽  
Vol 18 (05) ◽  
pp. 389-403 ◽  
Author(s):  
THOMAS D. JORGENSEN ◽  
BARRY P. HAYNES ◽  
CHARLOTTE C. F. NORLUND
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Networks ◽  
Robot Control ◽  
Complexity Measures ◽  
Information Theoretic ◽  
Pruning Method ◽  
The Neural Network ◽  
Artificial Neural ◽  
Pruning Technique

This paper describes a new method for pruning artificial neural networks, using a measure of the neural complexity of the neural network. This measure is used to determine the connections that should be pruned. The measure computes the information-theoretic complexity of a neural network, which is similar to, yet different from previous research on pruning. The method proposed here shows how overly large and complex networks can be reduced in size, whilst retaining learnt behaviour and fitness. The technique proposed here helps to discover a network topology that matches the complexity of the problem it is meant to solve. This novel pruning technique is tested in a robot control domain, simulating a racecar. It is shown, that the proposed pruning method is a significant improvement over the most commonly used pruning method Magnitude Based Pruning. Furthermore, some of the pruned networks prove to be faster learners than the benchmark network that they originate from. This means that this pruning method can also help to unleash hidden potential in a network, because the learning time decreases substantially for a pruned a network, due to the reduction of dimensionality of the network.

scholarly journals Neural Networks in Mechanical System Simulation, Identification, and Assessment

1993 ◽  
Vol 1 (2) ◽  
pp. 177-199 ◽  
Author(s):  
Thomas L. Paez
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
System Design ◽  
Mechanical System ◽  
System Simulation ◽  
Design Analysis ◽  
Control Problems ◽  
Artificial Neural ◽  
And Control

Artificial neural networks (ANNs) have been used in the solution of a variety of mechanical system design, analysis, and control problems. This paper describes the ANNs that have been most frequently used in mechanical system applications. It also summarizes some of the applications that have been developed for ANNs, and briefly reviews the literature where descriptions of the developments and applications can be found. Some recommendations regarding ANN applications in mechanical system simulation, identification, and assessment are provided.

Sign in / Sign up

Export Citation Format

Share Document