期刊文献+
任意字段
题名或关键词
题名
关键词
文摘
作者
第一作者
机构
刊名
分类号
参考文献
作者简介
基金资助
栏目信息

基于VHDL语言的神经网络激活函数随机运算的实现

Implementation of Activated Function of Neural Networks with Stochastic Arithmetic Theory Based on VHDL
下载PDF
导出
摘要 为节省硬件实现中的资源数量,基于状态机原理并采用随机运算实现神经网络非线性激活函数的方法,给出了S型激活函数的数字逻辑实现,用硬件描述语言(VHDL)对该算法进行了软件设计与实现,并在ModelsimSE6.2仿真平台上进行了仿真测试。该设计有利于程序的随时修改,可节省大量硬件乘法器,有效缩短设计周期,满足了神经网络超大规模集成电路的需要。 The method based on stochastic arithmetic was presented to implement the nonlinear activation function of neural networks for saving hardware resoures. This method was based on the principle of state machines. In the paper,the digital logic implemention of Sigmoid function was given,and then the software was designed in hardware description language VHDL. The simulations based on the platform（Modelsim SE 6.2）were carried out. Using this method,the program can be modified anytime, the development, period can shorten greatly and the hardware resoures can be saved significantly. This meets the neural network VLSI requirements well.
作者 初丽娟 沈艳霞
机构地区 江南大学电气与自动化研究所
出处 《江南大学学报（自然科学版）》 CAS 2009年第2期154-158,共5页 Joural of Jiangnan University (Natural Science Edition)　
基金 江苏省自然科学基金项目(BK2007540)
关键词 激活函数 随机算法 状态机 硬件描述语言 activation function, stochastic arithmetic, state machines, VHDL
分类号 TP183 [自动化与计算机技术—控制理论与控制工程]
  • 相关文献

参考文献12

  • 1Sung su Kim, Seul Jung. Hardware implementation of a real time neural network controller with a DSP and an FPGA [ C ]// IEEE International Conference on Robotics and Automation. New Orleans : [ s. n. I , 2004:4639- 4644.
  • 2WANG Qin-ruo,YI Bo,XIE Yun,et al. The hardware structure design of perceptren with FPGA implementation [ C]// IEEE International Conference on Systems. Man and Cybernetics, Piscataway: [ s. n. ] ,2003:762-767.
  • 3YUN S B, KIM Y J, DONGS S. Hardware implementation of neural network with expansible and reconfigurable architecture [ C ] // Proceedings of the 9^th International Conference on Neural Information Processing. Singapore: [ s. n. ] ,2002:970-975.
  • 4Hiroomi Hikawa. A digital hardware pulse-mode neuron with piecewise linear activation function [ J ]. IEEE Transactions on Neural Networks ,2003,14 ( 5 ) : 1028-1037.
  • 5Basterretxea k,Tarela J M, Campo del I. Approximation of sigmoid function and the derivative for hardware implementation of artificial neurons[ J ]. IEEE Proceedings on Circuits, Devices and Systems ,2004,151 (1) :18-24.
  • 6ZHANG Ming, Vassiliadis, Delqado Frias. Sigmoid generators for neural computing using piecewise approximations [ J ]. IEEE Transactions on Computers, 1996,45 ( 9 ) : 1045-1049.
  • 7Alippi C, Storti Gajani G. Simple approximation of sigmoidal functions realistic design of digital neural networks capable of learning[ C]// IEEE International Symposium on Circuits and Systems. Singapore : [ s. n. ], 1991 : 1505-1508.
  • 8陈曦,王高峰,刘克刚,徐江丰.基于混合CORDIC的神经网络激活函数的实现[J].华中科技大学学报（自然科学版）,2007,35(9):114-117. 被引量：2
  • 9夏欣,贾永刚,王素珍.RBF神经网络中指数函数e^x的FPGA实现[J].微计算机信息,2005,21(07Z):145-146. 被引量：6
  • 10ZHANG Da, LI Hui, Simom Y Foo. A simplified FPGA implementation of neural network algorithms integrated with stochastic theory for power electronics applications [ C ]//2005,31 st Annual Conference of IEEE ( Industrial Electronics Soeiety). Raleigh: [s. n. ] , 2005:1018-1023.

二级参考文献13

  • 1Thomas Risse.Numerics—interactive.2005.4.
  • 2Ray Andraka.A Survey of CORDIC algorithms for FPGA based computers.
  • 3.[EB/OL].http://www.xilinx.tom.,.
  • 4Jordan L. Holt Finite Precision Error Analysis of Neural Network Hardware Implementations. IEEE TRANSACTIONS ON COMPUTERS [J] ,VOL.42, NO.3, MARCH 1993.
  • 5Myers D J, Hutchinson R A. Efficient implementation of piecewise linear activation function for digital VLSI neural networks [J]. Electronics Letters, 1989, 25(24): 1 662-1 663.
  • 6Alippi C, Storti G G. Simple approximation of sigmoid functions: realistic design of digital VLSI neural networks[C] // Proceedings of IEEE Int Symp Circuits and Systems. New York:IEEE SSC Press, 1991:1 505-1 508.
  • 7Amin H, Curtis K, Hayes Gill B R. Piecewise linear approximation applied to nonlinear function of a neural network [J]. IEE Proceedings Circuits, Devices and Systems, 1997, 144(6):313-317.
  • 8Basterretxea K, Tarela J, del Campo I. Approximation of sigmoid function and the derivative for hardware implementation of artificial neurons[J]. IEE Proceedings of Circuits, Devices and Systems, 2004, 151(1):18-24.
  • 9Walther J. A unified algorithm for elementary functions[C]//Spring Joint Computer Conference. Berlin: Springer-Verlag, 1971: 379-385.
  • 10Walther J. A unified algorithm for elementary functions[C]//Spring Joint Computer Conference. Berlin: Springer-Verlag, 1971: 379-385.

共引文献6

江南大学学报（自然科学版）
2009年 第2期

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