Please wait a minute...
ZJUS-A
Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering)  2009, Vol. 10 Issue (2): 184-188    DOI: 10.1631/jzus.A0820238
Electrical & Electronic Engineering     
The most robust design for digital logics of multiple variables based on neurons with complex-valued weights
Wei-feng LÜ, Mi LIN, Ling-ling SUN
Institute of VLSI Design, Zhejiang University, Hangzhou 310027, China; College of Electronics and Information, Hangzhou Dianzi University, Hangzhou 310018, China
Download:     PDF (0 KB)     
Export: BibTeX | EndNote (RIS)      

Abstract  Neurons with complex-valued weights have stronger capability because of their multi-valued threshold logic. Neurons with such features may be suitable for solution of different kinds of problems including associative memory, image recognition and digital logical mapping. In this paper, robustness or tolerance is introduced and newly defined for this kind of neuron according to both their mathematical model and the perceptron neuron’s definition of robustness. Also, the most robust design for basic digital logics of multiple variables is proposed based on these robust neurons. Our proof procedure shows that, in robust design each weight only takes the value of i or −i, while the value of threshold is with respect to the number of variables. The results demonstrate the validity and simplicity of using robust neurons for realizing arbitrary digital logical functions.

Key words： Complex-valued weights      Multi-valued neurons (MVNs)      Digital logic      Robust design     
Received: 30 March 2008     
CLC:  TP183  
  TN431  
Service
E-mail this article
Add to my bookshelf
Add to citation manager
E-mail Alert
RSS
Articles by authors
Wei-feng LÜ
Mi LIN
Ling-ling SUN
Cite this article:

Wei-feng LÜ, Mi LIN, Ling-ling SUN. The most robust design for digital logics of multiple variables based on neurons with complex-valued weights. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2009, 10(2): 184-188.

URL:

http://www.zjujournals.com/xueshu/zjus-a/10.1631/jzus.A0820238     OR     http://www.zjujournals.com/xueshu/zjus-a/Y2009/V10/I2/184

[1] Jun-hai SHI, Zhi-dan ZHONG, Xin-jian ZHU, Guang-yi CAO. Robust design and optimization for autonomous PV-wind hybrid power systems[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2008, 9(3): 401-409.
[2] CAO Yan-long, YANG Jiang-xin, WU Zhao-tong, WU Li-qun. A robust tolerance design method based on process capability[J]. Journal of Zhejiang University-SCIENCE A (Applied Physics & Engineering), 2004, 5(1): 81-85.