课题基金 / 基金详情

Studies on the formation of intellectual concepts with neural network models.

Studies on the formation of intellectual concepts with neural network models.
用神经网络模型研究智力概念的形成。
批准号:
03831011
负责人:
KISHI Koichiro
金额:
$1.34万
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:
1991
资助国家:
日本
项目状态:
已结题
起止时间:
1991 至 1993

项目摘要

项目成果

KISHI Koichiro的其他基金

相似基金

相关文献

中文摘要
翻译
在大脑皮层中,人们认为信息是以神经元集合的活动模式来表示的。在这项研究中,为了调查的形成智能概念,这样的分布式表示被纳入一个神经网络的输出层与误差反向传播算法。该网络以完全准确的方式识别了学习数据。几个隐藏层的单元回应了一系列相关数据。该网络对隐藏层单元的失活表现出很高的容忍度。此外,它以高精度识别新构建的数据。这些结果表明,形成的智能概念与分布式表示的一些优势。在此基础上,结合认知神经科学的现有知识,提出了一种控制多元智能的递归神经网络模型。该模型具有多个神经网络,用于多个智能。来自多个输入的信息通过次级感觉层整合到高级联想层。高级联想层的输出被传送到过滤层,过滤层为每个次级感觉层提供每个瞬间的偏差,这些偏差指导了智力的连续表达。递归神经网络采用递归反向传播算法对学习数据集进行学习。经过学习,发现这个网络根据前面的命令处理输入数据。高级联想层中的信息表征可以看作是一种智力概念,有待进一步研究。
英文摘要
In the cerebral cortex, it is assumed that information is represented in the activity pattern of an assembly of neurons. In this study, in order to investigate the formation of intellectual concepts, such a distributed representation was incorporated in the output layr of a neural network with the error-back-propagation algorithm. The network recognized the learned data with complete accuracy. Several units of the hidden layr responded to a series of related data. The network showed high tolerance for the inactivation of the hidden layr units. In addition, it recognized the newly constructed data with high accuracy. These results showed some advantages of the formation of intellectual concepts with a distributed representation. Furthermore, according to the current knowledge of cognitive neuroscience, a recurrent neural network model for controlling multiple intelligence was proposed. The model had multiple neural networks for multiple intelligence. Information from multiple inputs was integrated in the higher association layr through secondary sensory layrs. The output of the higher association layr was transmitted to the filter layr, and the filter provided each secondary sensory layr with each momentary bias, which directed the successive expression of intelligence. The recurrent neural network learned the learning data set with the recurrent back-propagation algorithm. After learning, it was found that this network processed input data according to the previous command. The information representation in the higher association layr may be regarded as the intellectual concepts and will be analyzed in further studies.
期刊论文(52)
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:
Kishi, K., Sasaki, H.and Musha, T.: "EEG dipole tracing during cognitive processing of a visual letter." Jpn.J.Physiol.42(Suppl.). S169-S169 (1992)
Kishi, K.、Sasaki, H. 和 Musha, T.:“视觉字母认知处理过程中的脑电图偶极子追踪。”
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
共 25 条
    Analysis of the relationships between the DNase I or II enzymes and apoptosis
    • 批准号:
      12307011
    • 项目类别:
      Grant-in-Aid for Scientific Research (A)
    • 资助金额:
      $25.08万
    • 财政年份:
      2000
    • 负责人:
      KISHI Koichiro
    • 依托单位:
    Forensic Studies on a New Genetic Marker, Human DNase I
    • 批准号:
      10307010
    • 项目类别:
      Grant-in-Aid for Scientific Research (A)
    • 资助金额:
      $23.87万
    • 财政年份:
      1998
    • 负责人:
      KISHI Koichiro
    • 依托单位:
    Molecular-biological analysis of age-related markers present in body fluids and its forensic applications
    • 批准号:
      09357004
    • 项目类别:
      Grant-in-Aid for Scientific Research (A).
    • 资助金额:
      $18.11万
    • 财政年份:
      1997
    • 负责人:
      KISHI Koichiro
    • 依托单位:
    Forensic Studies on Identification of a Hit-and-Run Vehicle
    • 批准号:
      08407015
    • 项目类别:
      Grant-in-Aid for Scientific Research (A)
    • 资助金额:
      $9.47万
    • 财政年份:
      1996
    • 负责人:
      KISHI Koichiro
    • 依托单位:
    海外基金