Title :
Study on new evolutionary neural network
Author_Institution :
Wuhan Polytech Univ., China
Abstract :
The evolutionary neural network model can be generated combining the evolutionary computation with neural network. Based on analysis of merits and demerits of previously proposed evolutionary neural network models, and combining the immunized evolutionary programming proposed by the author, 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 :
genetic algorithms; neural nets; XOR problem; evolutionary computation; evolutionary neural network; genetic algorithm; immunized evolutionary programming; Algorithm design and analysis; Binary codes; Computer architecture; Computer networks; Electronic mail; Evolutionary computation; Genetic algorithms; Genetic programming; Neural networks; Next generation networking;
Conference_Titel :
Machine Learning and Cybernetics, 2003 International Conference on
Print_ISBN :
0-7803-8131-9
DOI :
10.1109/ICMLC.2003.1259687