课题基金 / 基金详情

Integrated synapse devices for fluxon neural networks

Integrated synapse devices for fluxon neural networks
用于 Fluxon 神经网络的集成突触设备
批准号:
05650322
负责人:
NAKAJIMA Koji
金额:
$1.54万
依托单位:
依托单位国家:
日本
项目类别:
Grant-in-Aid for General Scientific Research (C)
财政年份:
1993
资助国家:
日本
项目状态:
已结题
起止时间:
1993 至 1994

项目摘要

项目成果

NAKAJIMA Koji的其他基金

相似基金

相关文献

中文摘要
翻译
提出了一种基于SQUID的神经元和两种可变突触的新型超导电路。约瑟夫森电路以其极低的功耗实现高速运算,在神经网络的超大规模集成电路中具有上级优势。利用单结SQUID和双结SQUID的组合实现了具有良好输入输出隔离度和陡峭阈值特性的神经元电路,单结SQUID的量子态代表神经元的状态,双结SQUID的输出电压是S形函数,工作在带分流电阻的非锁存模式下.可变突触电路之一以数字方式改变其电导值。另一可变突触电路是可变电流源,其中输出电流可以数字地改变。两个突触回路都由多个分流的双结SQUID组成。除了电路特性的数值模拟,我们已经制作了超导神经芯片使用Nb/AlOx/Nb约瑟夫森结技术。成功地演示了每个元件和3位A/D转换器的基本操作。该A/D转换器的模拟输入频率高达100 kHz,受到我们高增益测量设备的限制。仿真结果表明,该网络对100 MHz以上的模拟输入有响应。以如此高的速度测试网络是我们未来的挑战之一。本文还讨论了一个基于Hebb规则的变电流源型突触学习系统。
英文摘要
Novel superconducting circuits for a neuron and two types of variable synapses, which are based on SQUIDs, are presented. Josephson circuits seem to be superior for VLSI of the neural networks because of the high-speed operation under very low power dissipation. A neuron circuit with good input-output isolation and steep threshold characteristics is accomplished using a combination of a single-junction SQUID coupled to a double-junction SQUID.The quantum state of the single-junction SQUID represents the neuron state, and output voltage of the double-junction SQUID,which is operated under a nonlatching mode with shunt resistors, is a sigmoid-shaped function. One of the variable synapse circuits changes its conductance value digitally. Another variable synapse circuit is a variable current source in which the output current can change digitally. Both synapse circuits consist of multiple shunted double-junction SQUIDs. Besides numerical simulations of the circuit characteristics, we have fabricated superconducting neural chips using a Nb/AIOx/Nb Josephson junction technology. The fundamental operation of each element and 3-bit A/D converter are successfully demonstrated. This A/D converter was operated with analog input frequency as high as 100kHz, limited by our high-gain measurement equipment. Simulation shows that this network responds to analog input at over 100MHz. Testing the network at such high speeds is one of our challenges in the future. A learning system based on Hebb's rule with variable-current-source type of synapse is also discussed.
期刊论文(48)
专著(0)
科研奖励(0)
会议论文
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
Y.Mizugaki: "Implementation of superconducting synapse into a neuro-based analog-to-digital converter" Appl.Phys.Lett.65. 1712-1713 (1994)
Y.Mizugaki:“将超导突触实现到基于神经的模数转换器”Appl.Phys.Lett.65。
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
S.Sato: "LSI Neural Chip of Pulse-Output Network with Programmable Synapse" IEICE Trans.ELECTRON.E78-C. 94-100 (1995)
S.Sato:“具有可编程突触的脉冲输出网络LSI神经芯片”IEICE Trans.ELECTRON.E78-C。
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
K. Nakajima: "Correct reaction neural network" Neural Networks. 6. 217-222 (1993)
K. Nakajima:“正确反应神经网络”神经网络。
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
18
    A Study of developing a framework for motivating university faculty for implementing e-learning by designing with ID models
    High speed logic and memory system based on pair-creation and -annihilation of shingle flux quanta
    • 批准号:
      24656221
    • 项目类别:
      Grant-in-Aid for Challenging Exploratory Research
    • 资助金额:
      $2.58万
    • 财政年份:
      2012
    • 负责人:
      NAKAJIMA Koji
    • 依托单位:
    Elucidation of keratinocyte differentiation and proliferation by splicing of transcritption factor.
    • 批准号:
      23791247
    • 项目类别:
      Grant-in-Aid for Young Scientists (B)
    • 资助金额:
      $2.75万
    • 财政年份:
      2011
    • 负责人:
      NAKAJIMA Koji
    • 依托单位:
    Expression regulation of basement membrane proteins by transcription factor of epithelial to mesenchymal transition
    • 批准号:
      21791055
    • 项目类别:
      Grant-in-Aid for Young Scientists (B)
    • 资助金额:
      $2.75万
    • 财政年份:
      2009
    • 负责人:
      NAKAJIMA Koji
    • 依托单位:
    海外基金