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Σ-Δ调制的比特流Hopfield人工神经网络及在片训练系统

Hopfield Neural Network Based on Σ-Δ Modulation and On-chip Training System
原文传递
导出
摘要 提出了一种基于Σ-Δ调制的单比特Hopfield人工神经网络(HNN)的设计方法.网络中各神经元的输入输出均为基于Σ-Δ调制的单比特信号,这解决了多比特并行分布网络扇入扇出的难题.同时在设计12神经元全并行Hopfield网络过程中,通过数字后端设计,优化了关键模块,减小了系统的面积及功耗.最后采用同步扰动学习算法(SLA)实现了在片训练系统,通过此训练系统Hopfield网络实现了文字的联想记忆. A design method for the bit-stream Hopfield neural network （HNN） based on ∑-△ modulation is presen- ted. The signals from the input and output of each neuron are represented by ∑-△ modulated single-bit streams. This single-bit representation alleviates the fan-in and fan-out issues typical of distributed systems. A parallel distributed network with 12 neurons is designed, and the whole HNN is implemented on a field pro- grammable gate array and hackend design. Several key modules of the systems are optimized and the area, power are reduced by using digital backend design. Moreover, the simultaneous learning algorithm （SLA） is used to train the HNN. The SLA is an on-chip learning algorithm and is implemented on board. The bit- stream HNN achieves rather precise character recognition and memorization after the training.
作者 郭晓丹 孟桥
机构地区 东南大学射频与光电集成电路研究所 东南大学射频集成电路与系统教育部工程研究中心
出处 《信息与控制》 CSCD 北大核心 2014年第1期1-8,共8页 Information and Control
基金 国家自然科学基金资助项目(61076118/F040805)
关键词 比特流 人工神经网络 HOPFIELD ∑-△ FPGA Astro bit-stream artificial neural network Hopfield ∑-△ FPGA Astro
分类号 TP18 [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20

  • 1Graf H P, Jaekel L D, Hubbard W E. VLSI implementation of a neural network modelJ]. Computer, 1988, 21 (3) : 41 -49.
  • 2Blayo F, Hurat P. A VLSI systolic array dedicated to Hopfietd neural network [ M ]//VLSI fir Artifieial Intelligence. Berlin, Germany: Springer1989 : 255 - 264.
  • 3Draghici S. Neural networks in analog hardware - Design and implementation issues[ J]. International Journal of Neural Systems, 2000, 10( 1 ) : 19 -42.
  • 4Vittoz E A. Analog VLSI implementation of neural networks [ C ]//IEEE International Symposium on Circuits and Systems. Piscataway, USA : IEEE, 1990 : 2524 - 2527.
  • 5Watanabe T, Kimura K, Aoki M, et al. A single 1.5-V digital chip for a 106 synapse neural network[ J]. IEEE Transactions on Neural Net- works, 1993, 4(3) : 387 -393.
  • 6Yasunaga M, Hachiya I, Moki K, et al. Fauh-tolerant self-organizing map implemented by wafer-scale integration [ J ]. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 1998, 6(2) : 257 -265.
  • 7Torralba A, Colodro F. Towards a fully parallel stochastic Hopfield neural network [ C ]//1993 IEEE International Symposium on Circuits and Systems. Piscataway, NJ, USA: IEEE, 1993 : 2741 -2743.
  • 8Maeda Y, Fukuda Y. FPGA implementation of pulse density Hopfield neural network[ C]//International Joint Conference on Neural Networks. Piscataway, N J, USA: IEEE, 2007 : 700 - 704.
  • 9Liang Y, Meng Q, Wang Z G, et al. Design of bit-stream neuron based on direct -E-A signal process[ C ]//International Conference on Wireless Communications & Signal Processing. Piscataway, NJ, USA : IEEE, 2009 : 1 - 3.
  • 10Liang Y, Wang Z G, Meng Q, et al. Design of high speed high SNR bit-stream adder based on E-A modulation[ J]. Electronics Letters, 2010, 46(11 ) : 752 -753.
信息与控制
2014年 第1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