期刊文献+

多阈值神经元电路设计及在多值逻辑中的应用 被引量:3

Circuits Design of Multi-Thresholded Neuron(MTN) and Its Applications in Mult-Valued Logic
下载PDF
导出
摘要 分析了多阈值神经元工作原理,并提出设计多阈值神经元电路的方法.首先,用两个 MOS晶体管组成电压型突触电路,然后又提出一种基于BiCMOS工艺的判别转换开关电路,这种电路以压控电流作为阈值信号,并实现电压到电流的转换.在此基础上,结合限幅电压开关理论提出多阈值神经元阈值判别函数电路的开关级设计方法.最后,从开关级设计了实现三值逻辑中文字、与、或三种基本运算的多阈值神经元电路,用这三种基本运算的多阈值神经元电路可实现任意三值函数的多阈值神经网络.文章还对设计出的电路用 PSPICE进行模拟,测量相关参数.模拟结果表明,该文设计的电路不仅实现了正确的逻辑功能,而且速度较快. By analysing the principle of muti-thresholded neurons (MTNs), a method was developed for designing muti-thresholded neuron circuits (MTNCs). First, the voltage-mode synapse circuit was designed using two MOS transistors. Second, a BiCMOS technics based circuit called verdict-converting switch (VCS) was put forward. The VCS has a threshold which is voltage-controlled current signal and it has the ability of converting the voltage signal to current signal. Based on this possibility, an approach was proposed for designing the circuits of multi-thresholded verdicting function (MTVF) at switch level. Finally, several MTNCs were designed for implementing the Literal, AND, OR operation as three basic operations in ternary logic at switch level. With these basic MTNCs, arbitrary ternary functions can be achieved by multi-thresholded neural networks. The result of simulation with PSPICE showed that the designed circuits had not only the correct logic function but also had small propagation delay.
出处 《计算机学报》 EI CSCD 北大核心 2005年第2期281-288,共8页 Chinese Journal of Computers
关键词 多阈值神经元 多值逻辑 基本运算 BICMOS电路 CMOS integrated circuits Electric currents Threshold logic Transistors Voltage control
  • 相关文献

参考文献22

  • 1沈杰,靳东明,李志坚.双MOS晶体管等效电阻[J].清华大学学报(自然科学版),1999,39(5):104-107. 被引量:3
  • 2高丽娜,邱关源.一种连续可调权值CMOS神经网络[J].电子学报,1998,26(2):120-122. 被引量:3
  • 3吴杰,邱关源.CMOS电流镜及其应用[J].湖南大学学报(自然科学版),1996,23(1):95-100. 被引量:6
  • 4王守觉.多值和多阈值神经元及其网络组合与应用[J].电子学报,1996,24(5):1-6. 被引量:15
  • 5Lau Clifford ed. Neural networks: Theoretical foundation and analysis. A Selected Preprint Volume, Neural Networks Council, Sponsor, IEEE Press, 1992.
  • 6Gisutham B., Srikanthan T., Asari K.V. A high speed flat CORCIC based neuron with multi-level activation function for robust pattern recognition. In: Proceedings of the 5th IEEE International Workshop on Computer Architectures for Machine Perception, Padova, 2000, 87~94.
  • 7Moraga C., Heider R. New lamps for old!(generalized multiple-valued neurons). In: Proceedings of the 29th IEEE International Symposium on Multiple-Valued Logic, Freiburg, 1999, 36~41.
  • 8Yuh J., Newcomb R.W. Circuits for multi-level neuron nonlinearities. In: Proceedings of International Joint Conference on Neural Networks, Baltimore, 1992, 2: 27~32.
  • 9Au R., Yamashita T., Shibata T., Ohmi T. Neuron-MOS multiple-valued memory technology for intelligent data processing. In: Proceedings of the 41st IEEE International Solid-State Circuits Conference, San Francisco, 1994, 270~271.
  • 10Ngom A., Stojmenovic I., Obradovic Z. Minimization of multivalued multithreshold perceptrons using genetic algorithms. In: Proceedings of the 28th IEEE International Symposium on Multiple-Valued Logic, Fukuoka,1998, 209~214.

二级参考文献7

  • 1张建人.MOS集成电路分析与设计[M].北京:电子工业出版社,1985..
  • 2沈杰 靳东明 等.可编程模糊控制器的设计.中国第六届多值逻辑学术会议论文[M].北京:中国计算机学会多植逻辑专业委员会,1994..
  • 3邱关源,电网络理论,1988年
  • 4杨行峻,人工神经网络,1992年
  • 5吴佑寿
  • 6沈杰,中国第六届多值逻辑学术会议论文集,1998年
  • 7张建人,MOS集成电路分析与设计,1985年

共引文献23

同被引文献36

  • 1姜楠,章照止.多值多门限神经元函数的相关性和频谱分析[J].北京工业大学学报,2009,35(4):549-554. 被引量:1
  • 2王守觉.多值和多阈值神经元及其网络组合与应用[J].电子学报,1996,24(5):1-6. 被引量:15
  • 3Yuh J,Newcomb R W.Circuits for multi-level neuron non-linearities[A].In:Proceedings of International Joint Conference on Neural Networks[C].Baltimore,1992,2:27-32.
  • 4Au R,Yamashita T,Shibata T,Ohmi T.Neuron-MOS multiple-valued memory technology for intelligent data processing[A].In:Proceedings of the 41^st IEEE International Solid-State Circuits Conference[C).San Francisco,1994,270-271.
  • 5Ngom A,Stojmenovic I,Obradovic Z.Minimization of multivalued multihreshold perceptrons using genetic algorithms[A].In:Proceedings of the 28^th IEEE International Symposium on Multiple-Valued Logic[C].Fukuoka,1998.209-214.
  • 6Donald L.Gray,Anthony N.Miched.A training algorithm for binary feedforward neural networks[J].IEEE Trans.N N.,1992,3(2):176-194.
  • 7W Penny,T J Stonham.Storage capacity of multilayer Boolean neural networks[J].IEE Electronics Letters,1993,29(15).
  • 8Wang Shoujue,et al.A study on artificial neurons with multi-threshold transfer functions[J].Chinese journal of Electruics,1995,4(2):83-85.
  • 9NGOM A, STOJMENOVIC l, MILUTINOVIC V. STRIP: a strip-based neural-network growth algorithm for learning multiple-valued functions[ J]. IEEE Transactions on Neural Networks, 2001, 12(2) : 212-227.
  • 10OJHA P. Enumeration of linear threshold functions from the lattice of hyperplane intersections [ J ]. IEEE Transactions on Neural Networks, 2000, 11 (4) : 839- 850.

引证文献3

二级引证文献2

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部