Coherent neural networks : Construction of prototypal subsystems
相干神经网络:原型子系统的构建
基本信息
- 批准号:08555098
- 负责人:
- 金额:$ 8.9万
- 依托单位:
- 依托单位国家:日本
- 项目类别:Grant-in-Aid for Scientific Research (A)
- 财政年份:1996
- 资助国家:日本
- 起止时间:1996 至 1997
- 项目状态:已结题
- 来源:
- 关键词:
项目摘要
Brain-type information processing systems are actively studied widely, although there is no clear definition of the "brain-type systems'yet. The expected brain-type systems will be, at least, complementary to the so-called von-Neumann-type systems. In other words, the most expected feature of the future brain-type systems should be a distributed and flexible (self-organizing and/or learning) information processing based on a highly parallel architecture. That is to say, we have to realize a massively parallel and flexible hardware which has its own basis outside the Turing machine principle.The research project aims at a construction of the prototypal subsystems of the future brain-type systems by way of realizing neural networks using wave fields such as lightwave and electromagnetic wave ; i.e., the coherent neural networks. The coherent neural networks are an expansion of the complex-valued neural networks proposed by the applicant's research group in 1992. In the present project, we have been aiming to establish the theoretical basis of the dynamic behavior of the lightwave (or electromagnetic-wave/electron-wave) coherent neural networks in which the amplitude and the phase of the information carrier are manipulated, and to realize the prototypal subsystem hardware.In the two-year research, we have (1) elucidated the mechanism of the behavioral instability, (2) proposed and demonstrated a novel learning method to suppress the instability. We have also (3) constructed a radar system that has a complex-amplitude information processing stage by which the dynamics relation between the physics of electromagnetic wave and the complex-valued neural networks can be elucidated. The aims of this project are considered almost accomplished by these fruitful results. We expect that further theoretical and experimental research on the next stage will be carried out for constructing a more realistic coherent neural networks.
脑型信息处理系统的研究十分活跃,但“脑型系统”的概念至今还没有一个明确的定义。预期中的脑型系统至少将是所谓冯-诺依曼型系统的补充。换句话说,未来脑型系统最令人期待的特征应该是基于高度并行架构的分布式和灵活的(自组织和/或学习)信息处理。也就是说,我们必须实现一种在图灵机原理之外有自己基础的大规模并行和灵活的硬件。该研究项目旨在通过使用光波和电磁波等波场实现神经网络来构建未来脑型系统的原型子系统,即,相干神经网络相干神经网络是申请人的研究小组在1992年提出的复值神经网络的扩展。在本项目中,我们的目标是建立光波动态行为的理论基础(或电磁波/电子波)相干神经网络,其中信息载体的幅度和相位被操纵,并实现原型子系统硬件。在两年的研究中,我们(1)阐明了行为不稳定性的机制,(2)提出并论证了一种新的抑制不稳定性的学习方法。我们还(3)构造了一个具有复振幅信息处理阶段的雷达系统,通过该雷达系统可以阐明电磁波物理与复值神经网络之间的动力学关系。这些丰硕的成果使本项目的目标基本实现。我们期待下一阶段进一步的理论和实验研究能够为构造更符合实际的相干神经网络而展开。
项目成果
期刊论文数量(52)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
A.Hirose, H.Onishi: "Behavior stability and time-sequential signal variation of recurrent complex-valued neural networks" Int'l Conf.on Comput.Intelligence and Neuroscience (ICCIN)'97 Proc.2,134-137 (Mar.2-5,1997, Research Triangle Park).
A.Hirose、H.Onishi:“循环复值神经网络的行为稳定性和时间序列信号变化”国际计算智能与神经科学会议 (ICCIN)97 Proc.2,134-137(Mar.2)
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
A.Hirose: "Two-dimensional Hodgkin-Huxley equations for investigating a basis of pulse-processing neural networks" Int'l Conf.on Artificial Neural Networks (ICANN) '97. Proc. 85-90 (1997)
A.Hirose:“用于研究脉冲处理神经网络基础的二维 Hodgkin-Huxley 方程”国际人工神经网络会议 (ICANN) 97。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
A.Hirose, H.Onishi: "Behavior stabilization of complex-valued recurrent neural networks using relative-minimization learning" Int'l Joint Conf.on Neural Networks (IJCNN) '98. (to be presented). A.Hirose (1998)
A.Hirose、H.Onishi:“使用相对最小化学习实现复值循环神经网络的行为稳定性”国际神经网络联合会议 (IJCNN) 98。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
A.Hirose R.Eckmiller: "Coherent optical neural networks" Int′l Conf.on Optical Computing ′96. 2. 6-7 (1996)
A.Hirose R.Eckmiller:“相干光学神经网络”国际光学计算大会 96. 2. 6-7 (1996)。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
A.Hirose S.Murakami: "Mesoscopic analysis and synthesis of membrane potential dynamics using two-dimonsional Hodgkin-Huxloy oquations" Int'l Conf.on Neural Infomation processing(ICONP) '97. Proc.22. 202-205 (1997)
A.Hirose S.Murakami:“使用二维 Hodgkin-Huxloy 方程对膜势动力学进行介观分析和合成”国际神经信息处理会议 (ICONP) 97。
- DOI:
- 发表时间:
- 期刊:
- 影响因子:0
- 作者:
- 通讯作者:
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
数据更新时间:{{ journalArticles.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ monograph.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ sciAawards.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ conferencePapers.updateTime }}
{{ item.title }}
- 作者:
{{ item.author }}
数据更新时间:{{ patent.updateTime }}
HIROSE Akira其他文献
HIROSE Akira的其他文献
{{
item.title }}
{{ item.translation_title }}
- DOI:
{{ item.doi }} - 发表时间:
{{ item.publish_year }} - 期刊:
- 影响因子:{{ item.factor }}
- 作者:
{{ item.authors }} - 通讯作者:
{{ item.author }}
{{ truncateString('HIROSE Akira', 18)}}的其他基金
The mechanisms for the progression of hepatic fibrosis through AGE-RAGE system and renin-angiotensin system
AGE-RAGE系统和肾素-血管紧张素系统促进肝纤维化进展的机制
- 批准号:
26461011 - 财政年份:2014
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Involvement of renin-angiotensin system for the development of NASH
肾素-血管紧张素系统参与 NASH 的发生
- 批准号:
22790650 - 财政年份:2010
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Young Scientists (B)
Low direction-coupling array antenna for use in plastic landmine visualization system
用于塑料地雷可视化系统的低方向耦合阵列天线
- 批准号:
22651062 - 财政年份:2010
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Challenging Exploratory Research
Adaptive millimeter-wave security imaging based on complex-valued neural networks
基于复值神经网络的自适应毫米波安全成像
- 批准号:
21300089 - 财政年份:2009
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
Basic research on elimination of artifacts in ultrasonic imaging based on spatiotemporal CMRF model
基于时空CMRF模型的超声成像伪影消除基础研究
- 批准号:
18360162 - 财政年份:2006
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Scientific Research (B)
Development of a plastic landmine detection system based on CMRF model
基于CMRF模型的塑料地雷探测系统的研制
- 批准号:
15206047 - 财政年份:2003
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Scientific Research (A)
Fundamental study on neural chips that processes high-frequency carrier signals adaptively and nonlinearly
自适应非线性处理高频载波信号的神经芯片基础研究
- 批准号:
13835002 - 财政年份:2001
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
Fundamental studies on quantum neural devices
量子神经器件基础研究
- 批准号:
07650393 - 财政年份:1995
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Scientific Research (C)
相似海外基金
Sub-picosecond region two dimensional parallel information processing in photorefractive crystals
光折变晶体中的亚皮秒区二维并行信息处理
- 批准号:
05452108 - 财政年份:1993
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for General Scientific Research (B)
Development of Wideband Acoustooptic Integrated Circuits for Parallel Information Processing
并行信息处理宽带声光集成电路的研制
- 批准号:
02555082 - 财政年份:1990
- 资助金额:
$ 8.9万 - 项目类别:
Grant-in-Aid for Developmental Scientific Research (B)
PARALLEL INFORMATION PROCESSING OF THE VISUAL SYSTEM
视觉系统的并行信息处理
- 批准号:
6518269 - 财政年份:1979
- 资助金额:
$ 8.9万 - 项目类别:
PARALLEL INFORMATION PROCESSING OF THE VISUAL SYSTEM
视觉系统的并行信息处理
- 批准号:
6384258 - 财政年份:1979
- 资助金额:
$ 8.9万 - 项目类别:
PARALLEL INFORMATION PROCESSING OF THE VISUAL SYSTEM
视觉系统的并行信息处理
- 批准号:
6178353 - 财政年份:1979
- 资助金额:
$ 8.9万 - 项目类别:
PARALLEL INFORMATION PROCESSING OF THE VISUAL SYSTEM
视觉系统的并行信息处理
- 批准号:
2752311 - 财政年份:1979
- 资助金额:
$ 8.9万 - 项目类别: