[1]ZHANG Xiu-ling,ZHANG Zhi-qiang.A novel method of optimal designing DHNN and applied to flatness pattern recognition[J].CAAI Transactions on Intelligent Systems,2008,3(3):250-253.
Copy
A novel method of optimal designing DHNN and applied to flatness pattern recognition
CAAI Transactions on Intelligent Systems[ISSN 1673-4785/CN 23-1538/TP] Volume:
3
Number of periods:
2008 3
Page number:
250-253
Column:
学术论文—机器感知与模式识别
Public date:
2008-06-25
- Title:
- A novel method of optimal designing DHNN and applied to flatness pattern recognition
- Keywords:
- discrete Hopfield neural networks（DHNN）; random destabilization optimal designing; Legendre orthodoxy polynomials; flatness pattern
- CLC:
- TP18
- DOI:
- -
- Abstract:
- A novelmethod of op timal designingDHNN is p roposed based on random destabilization and its associa2 tive memory. Thismethod reduces the harshness requirement of the weightmatrix and avoids getting into the p seudo stability point. The method is app lied to flatness pattern recognition. Denote seven kinds of basis flatness modes thatmeet with usually by Legendre orthodoxy polynomials, don’t need more samp le in training the network. It is a more simp le and availabilitymethod in flatness pattern recognition and makes reference for carrying out the flatness control. Simulation result shows thisway is p racticable.
- References:
-
[1] 张秀玲,刘宏民. 板形模式识别的GA-BP模型和改进的最小二乘法[J]钢铁, 2003,(10) .
[2] 李雪耀,王治平. Hopfield网络的稳定性优化计算研究[J]哈尔滨工程大学学报, 1998,(06) .
[3] 卢秉林. 板形—板厚综合控制方法的探讨[J]冶金设备, 2002,(04) .
[4] Chang Shengjiang. Adaptive Clipping for Neural Associative Memories .Chinese Journal of Lasers. 1997,4, (4) :372-377 .
- Similar References:
Memo
-
Last Update:
2009-05-14