Computational Research on Cognition and Memory Mechanism in Neural Networks with Asymmetric and Symmetric Network Structures

非对称和对称网络结构神经网络认知记忆机制的计算研究

基本信息

  • 批准号:
    17500154
  • 负责人:
  • 金额:
    $ 2.24万
  • 依托单位:
  • 依托单位国家:
    日本
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
  • 财政年份:
    2005
  • 资助国家:
    日本
  • 起止时间:
    2005 至 2006
  • 项目状态:
    已结题

项目摘要

In the neural networks, a parallel processing with nonlinear characteristics for the spatial information will be a fundamental principle of the visual information processing. It is not well discussed theoretically to clarify the key features for the parallel processing with nonlinear characteristics in the neural networks. In this research, it is shown that the asymmetrical nonlinear functions in the cascaded network with two network layers, play an crucial role in the parallel processing in the movement detection. Then, an ensemble processing of the parallel processing, is newly developed here. We made clear that the parallel processing with the even and odd nonlinear functions, is an effective in the-movement detection. The visual cortex for the movement detection, consists of two layered networks, called the primary visual cortex (V1), followed by the middle temporal area (MT). The fundamental characteristics of the neural network structure in V1 and MT of the visual cortex, is an asymmetrical network with a nonlinear pathway and a linear pathway The model neurons, clarified by Prof Naka at New York York University are discussed by analyzing the asymmetric neural networks. Then the analysis method was applied to the visual cortex networks. The V1 and MT model networks, are decomposed into sub-asymmetrical networks. By the optimization of the asymmetric networks, the movement detection equations are derived. Then, it was clarified that the ensemble parallel processing with the even-odd nonlinearity combined asymmetric networks in the V1 and MT, are fundamental in the movement detection. It was concluded that the ensemble parallel processing of V1 network, followed by the MT network, process the movement information sufficiently from the view point of the computational aspects. The ensemble processing developed here was applied to the text mining problems
在神经网络中,对空间信息的非线性并行处理将成为视觉信息处理的基本原则。对于神经网络中具有非线性特征的并行处理,理论上还没有很好的讨论。在这项研究中,它是不对称的非线性函数的级联网络中的两个网络层,在运动检测的并行处理中起着至关重要的作用。然后,在这里新开发了并行处理的集成处理。我们明确了奇偶非线性函数的并行处理,是一种有效的运动检测方法。用于运动检测的视觉皮层由两层网络组成,称为初级视觉皮层(V1),其次是中颞区(MT)。视觉皮层V1和MT神经网络结构的基本特征是具有非线性通路和线性通路的非对称网络。通过分析非对称神经网络,讨论了约克大学纽约教授纳卡阐明的模型神经元。然后将该分析方法应用于视皮层网络。将V1和MT模型网络分解为次非对称网络。通过对非对称网络的优化,推导出运动检测方程。然后,澄清了V1和MT中的奇偶非线性组合非对称网络的总体并行处理是运动检测的基础。从计算角度来看,V1网络的集成并行处理,其次是MT网络,可以充分处理运动信息。本文提出的集成处理方法被应用于文本挖掘问题

项目成果

期刊论文数量(23)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
Neural Computations by Asymmetric Networks with Nonlinearities
  • DOI:
    10.1007/978-3-540-71629-7_5
  • 发表时间:
    2007-04
  • 期刊:
  • 影响因子:
    0
  • 作者:
    N. Ishii;Toshinori Deguchi;M. Kawaguchi
  • 通讯作者:
    N. Ishii;Toshinori Deguchi;M. Kawaguchi
Text Classification: Combining Grouping, LSA and kNN vs Support Vector Machine
  • DOI:
    10.1007/11893004_51
  • 发表时间:
    2006-10
  • 期刊:
  • 影响因子:
    0
  • 作者:
    N. Ishii;Takeshi Murai;T. Yamada;Y. Bao;Susumu Suzuki
  • 通讯作者:
    N. Ishii;Takeshi Murai;T. Yamada;Y. Bao;Susumu Suzuki
Direction selective ergonomics and human factors - a layout for analog VLSI
方向选择性人体工程学和人为因素 - 模拟 VLSI 的布局
Direction selective ergonomics and human factors-a layout for analog VLSI
方向选择性人体工程学和人为因素——模拟超大规模集成电路的布局
Text Classification by Combining Different Distance Functions with Weights
{{ 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 }}

ISHII Naohiro其他文献

ISHII Naohiro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('ISHII Naohiro', 18)}}的其他基金

Computational Study on the Cognition and Memory Based on the Nonlinear Analysis for the Asymmetric Neural Networks
基于非对称神经网络非线性分析的认知与记忆计算研究
  • 批准号:
    15K00351
  • 财政年份:
    2015
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Computational Studies on the Cognition and Memory Mechanisms of the Layered Neural Network with Asymmetric Structure
非对称结构分层神经网络认知记忆机制的计算研究
  • 批准号:
    21500225
  • 财政年份:
    2009
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Computational Study on Recognition and Memory Mechanism of Asymmetric and Symmetric Layered Neural Networks
非对称与对称分层神经网络识别与记忆机制的计算研究
  • 批准号:
    19500197
  • 财政年份:
    2006
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Computational Research on Cognition and Memory Mechanism in Neural Networks with Symmetric and Asymmetric Network Structures
对称与非对称网络结构神经网络认知与记忆机制的计算研究
  • 批准号:
    15500134
  • 财政年份:
    2003
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Computational Study on Recognition and Memory in the Asymmetric <symmetric Neural Networks
非对称<对称神经网络识别与记忆的计算研究
  • 批准号:
    12680379
  • 财政年份:
    2000
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Computational Study on the Structure and Learning in the Integrated Neural Networks for Different Sensors
不同传感器的集成神经网络结构和学习的计算研究
  • 批准号:
    09680365
  • 财政年份:
    1997
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Developmental Study on Measuring, Recording & Procession System of EEG during Working and Sleep
测量、记录的发展研究
  • 批准号:
    03555068
  • 财政年份:
    1991
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Developmental Scientific Research (B)
Study of Neural Information Processing by Spacial-Temporal Computation of Electroencephalogram, Electrooculogram and Electromyogram
脑电图、眼电图、肌电图时空计算的神经信息处理研究
  • 批准号:
    01550328
  • 财政年份:
    1989
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for General Scientific Research (C)
Development Studies of Measuring and Processing Systgem of EEG Activity during Orking and Sleeping
睡眠时脑电活动测量与处理系统的开发研究
  • 批准号:
    61850055
  • 财政年份:
    1986
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for Developmental Scientific Research
Study of Information Processing in Neural Systems by Measuring EEG,EOG and EMG.
通过测量脑电图、眼电图和肌电图研究神经系统的信息处理。
  • 批准号:
    61550296
  • 财政年份:
    1986
  • 资助金额:
    $ 2.24万
  • 项目类别:
    Grant-in-Aid for General Scientific Research (C)
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了