DocumentCode
554108
Title
Notice of Retraction
Neural Network optimized with a self-adaptive Differential Evolution Algorithm for PID controller
Author
Peng Guo ; Zheng Zhao
Author_Institution
Sch. of Comput. Sci. & Technol., Tianjin Univ., Tianjin, China
Volume
2
fYear
2011
fDate
26-28 July 2011
Firstpage
668
Lastpage
672
Abstract
Notice of Retraction
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Input layer weights and hidden layer weights of Neural Network are important to its performance, but selections of these weights depend on experiences and trials, in this paper we present a method to optimize weights of Back-Propagation Neural Network. Input layer weights and hidden layer weights are generated randomly in initialization and optimized with self adaptive parameter Differential Evolution (selfDE-F). We test this method with PID controller simulation and compare its results with those from classical DE optimized Neural Network and jDE optimized Neural Network, experimental results show improvement of our approach.
After careful and considered review of the content of this paper by a duly constituted expert committee, this paper has been found to be in violation of IEEE´s Publication Principles.
We hereby retract the content of this paper. Reasonable effort should be made to remove all past references to this paper.
The presenting author of this paper has the option to appeal this decision by contacting TPII@ieee.org.
Input layer weights and hidden layer weights of Neural Network are important to its performance, but selections of these weights depend on experiences and trials, in this paper we present a method to optimize weights of Back-Propagation Neural Network. Input layer weights and hidden layer weights are generated randomly in initialization and optimized with self adaptive parameter Differential Evolution (selfDE-F). We test this method with PID controller simulation and compare its results with those from classical DE optimized Neural Network and jDE optimized Neural Network, experimental results show improvement of our approach.
Keywords
evolutionary computation; neural nets; self-adjusting systems; three-term control; PID controller; backpropagation neural network; hidden layer weights; input layer weights; self adaptive parameter differential evolution; self-adaptive differential evolution algorithm; Algorithm design and analysis; Artificial neural networks; Computer science; Optimization; Training; Tuning; Differential Evolution; Neural Network; PID controller; self adaptive parameter;
fLanguage
English
Publisher
ieee
Conference_Titel
Natural Computation (ICNC), 2011 Seventh International Conference on
Conference_Location
Shanghai
ISSN
2157-9555
Print_ISBN
978-1-4244-9950-2
Type
conf
DOI
10.1109/ICNC.2011.6022295
Filename
6022295
Link To Document