[an error occurred while processing this directive]
   
 
���¿��ټ��� �߼�����
   ��ҳ  �ڿ�����  ��ί��  Ͷ��ָ��  �ڿ�����  ��������  �� �� ��  ��ϵ����
�������պ����ѧѧ�� 2004, Vol. 30 Issue (11) :1101-1105    DOI:
���� ����Ŀ¼ | ����Ŀ¼ | ������� | �߼����� << | >>
���ͽ���������ģ��
����*
�人��ҵѧԺ �人 430023
New evolutionary neural networks
Gao Wei*
Wuhan Polytechnic University, Wuhan 430023, China

ժҪ
�����
�������
Download: PDF (142KB)   HTML 1KB   Export: BibTeX or EndNote (RIS)      Supporting Info
ժҪ Ŀǰ�Ľ���������ģ�ʹ������Ŵ��㷨��������������.���о�����,���ֽ�������������Ŵ����롢�Ŵ�����������ṹ���ƵȺܶ�����;�����ý����滮��һ�ֺܺõ�;��.���ڴ�,Ϊ�˿˷���ͳ�����滮�㷨�IJ���,�����������Ŀ������߽����滮�����һ����������Ȩֵ�������˽ṹͬʱ�����Ż������ͽ���������ģ��.���,ͨ�����͵�����������(XOR)�Ƚ��˸�ģ��ͬBP�����缰��ͳ����������ļ�������,�������������㾫�Ⱥ�,���Ҽ���Ч�ʸ�.
Service
�ѱ����Ƽ�������
�����ҵ����
�������ù�����
Email Alert
RSS
�����������
�ؼ����� ����������   �����滮   �Ŵ��㷨   ���߽����滮     
Abstract�� Nowadays, the genetic algorithm is a main evolutionary algorithm in ev olutionary neural network study. But the previous researches show that, this kin d of evolutionary neural network model have many shortcomings, such as genetic c ode problem, genetic operation problem and restriction on structure of neural ne twork, \%et al\%. And the evolutionary programming is a good method. To overcome the shortcomings of traditional evolutionary programming, combining the immunized e volutionary programming proposed by author and BP neural network, a new evolutio nary neural network model whose architecture and connection weights evolve simul taneously was proposed. Through the typical XOR problem, the new model was compa red and analyzed with BP neural network and traditional evolutionary neural netw ork. The computing results show that the precision and efficiency of the new mod el are all good.
Keywords�� evolutionary neural network   evolutionary programming   genetic algori thm   immunized evolutionary programming     
Received 2004-06-25;
About author: �� �� (1971-),��,������ƽ��,������, wgaowh@hotmail.com.
���ñ���:   
����.���ͽ���������ģ��[J]  �������պ����ѧѧ��, 2004,V30(11): 1101-1105
Gao Wei.New evolutionary neural networks[J]  JOURNAL OF BEIJING UNIVERSITY OF AERONAUTICS AND A, 2004,V30(11): 1101-1105
���ӱ���:  
http://bhxb.buaa.edu.cn//CN/     ��     http://bhxb.buaa.edu.cn//CN/Y2004/V30/I11/1101
Copyright 2010 by �������պ����ѧѧ��