DocumentCode :
1837784
Title :
New evolutionary neural networks
Author :
Gao, Wei
Author_Institution :
Wuhan Polytech. Univ., China
fYear :
2005
fDate :
26-28 May 2005
Firstpage :
167
Lastpage :
171
Abstract :
The evolutionary neural network can be generated combining the evolutionary computation and neural network. Based on analysis of merits and demerits of previously proposed evolutionary neural network models, combining the immunized evolutionary programming proposed by author and BP neural network, a new evolutionary neural network model whose architecture and connection weights evolve simultaneously is proposed. At last, through the typical XOR problem, the new model is compared and analyzed with BP neural network and traditional evolutionary neural network. The computing results show that the precision and efficiency of the new model are all good.
Keywords :
backpropagation; evolutionary computation; neural nets; XOR problem; connection weights; evolutionary computation; evolutionary neural network; immunized evolutionary programming; neural network architecture; Algorithm design and analysis; Competitive intelligence; Computer architecture; Computer networks; Evolutionary computation; Genetic algorithms; Genetic programming; Intelligent networks; Neural networks; Next generation networking;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Neural Interface and Control, 2005. Proceedings. 2005 First International Conference on
Print_ISBN :
0-7803-8902-6
Type :
conf
DOI :
10.1109/ICNIC.2005.1499869
Filename :
1499869
Link To Document :
بازگشت