课题基金 / 基金详情

Selective Binding, Generalization/Abstraction, and Internal Model Creation by means of Network Structure Pruning

Selective Binding, Generalization/Abstraction, and Internal Model Creation by means of Network Structure Pruning
通过网络结构剪枝的选择性绑定、泛化/抽象和内部模型创建
批准号:
15500139
负责人:
YASUI Syozo
金额:
$1.66万
依托单位国家:
日本
项目类别:
Grant-in-Aid for Scientific Research (C)
财政年份:
2003
资助国家:
日本
项目状态:
已结题
起止时间:
2003 至 2004

项目摘要

项目成果

YASUI Syozo的其他基金

相似基金

相关文献

中文摘要
翻译
对于人工神经网络,剪枝由于经济、简化、泛化能力强等原因而显得重要,目前已有许多算法。修剪也发生在真实的大脑中,被认为是冗余减少原则的一种形式,该原则可能是许多高级大脑功能的基础。从这个角度出发,我们考虑了选择的绑定、整合、抽象和内模归纳等相互关联的主题。特别是,我们利用这位首席研究员早先设计的称为CSDF的剪枝算法处理了以下子项目。(1)类比学习/推理类比已经在心理学、认识论、教育学、科学史和认知科学等不同领域进行了研究。人工智能方法也存在,但这种基于规则的尝试往往是杂乱无章的,并受到组合爆炸和其他问题的困扰。在此基础上,我们提出了一种新的方法,称为ABSTR…更基于动作的Connectionist类比处理器(AB-CAP)。作为剪枝学习的结果,AB-CAP自动创建内部抽象模型,并在具体实体和抽象实体之间建立适当的绑定。例如,内部模型充当新的相关数据集的吸引子,使AB-CAP能够处理多个类比。盲源分离(BSS)是一种新的信息技术创新,它可以从传感器观测到的混合信号中提取原本未知的信号。这项研究开发的方法与现有的基于信息/概率理论的方法有根本的不同。它使用一个自动编码器神经网络来最小化与以传感器信号为输入向量的输入-输出身份映射相关的误差。译码部分采用CSDF算法。在CSDF修剪中幸存下来的隐藏的非线性单元将是盲信号提取器。此外,解码器矩阵重构外部混合矩阵,使得解码器部分可以被解释为整个外部情况的内部模型。仿真实例表明,该方法具有很强的适应性和鲁棒性。(3)SOM的应用最近,本课题组将SOM的范式从向量空间推广到函数空间。这称为mnSOM。我们一直在考虑将CSDF修剪纳入与mnSOM相关的竞争性学习。这一部分还有待于取得成功。较少
英文摘要
For artificial neural networks, pruning is important for reasons of economy, simplification, generalization ability and so on, and a number of algorithms are available today. Pruning occurs in real brains as well, and is thought to be one form of the Principle of Redundancy Reduction that presumably underlies many higher-order brain functions. From this standpoint, we have considered such inter-related subjects as selected binding, integration, abstraction and internal model induction. In particular, we have dealt with the following sub-projects by using a pruning algorithm called CSDF devised earlier by this principal investigator.(1)Analogical Learning/InferenceAnalogy has been studied in various areas including psychology, epistemology, pedagogy, science history, and cognitive science. AI approaches also exist but such rule-based attempts tend to be bruit-force ones and suffer from combinatorial explosion and other problems. Based on CSDF, we have developed a new method called Abstr … More action-Based Connectionist Analogy Processor (AB-CAP). As a result of the learning with the pruning, AB-CAP automatically creates an internal abstraction model as well as induces proper bindings between concrete and abstract entities. For instance, the internal model acts as an attractor of new relevant dataset, to allow AB-CAP to be able to deal with multiple analogies. These features have been demonstrated by a number of examples.(2)Blind Source Separation(BSS)BSS is a new IT innovation by which to extract otherwise unknown signals from their mixtures observed by sensors. The method developed in this study is fundamentally different from existing ones that are all based on information/probability theories. It uses an auto-encoder neural net which minimizes the error associated with the input-output identity mapping with the sensor signals as the input vector. CSDF is applied to the decoder part. The hidden nonlinear units that have survived the CSDF pruning will be the blind signal extractors. Furthermore, the decoder matrix reconstructs the external mixing matrix, so that the decoder part can be interpreted as an internal model of the whole external situation. The method has high adaptability and robustness, as has been shown by many simulation examples including audio and visual real-world data.(3)Application to SOMRecently, this research group has generalized the paradigm of SOM from the vector space to function space. This is called mnSOM. We have been considering incorporation of the CSDF pruning into the competitive learning associated with mnSOM. Successful results remain to be made for this part. Less
期刊论文(107)
专著(0)
科研奖励(0)
会议论文
モジュラーネットワークSOMによる音階のマッピング
使用模块化网络 SOM 进行比例映射
DOI: --
发表时间: 2005
期刊: 電子情報通信学会技術研究報告 MBE2004-76
影响因子: --
作者: [徳永 憲洋, 森山 健一郎]
通讯作者: 森山 健一郎
Blind source separation by sensor-signal identity mapping with hidden-unit pruning.
通过传感器信号恒等映射和隐藏单元修剪进行盲源分离。
DOI: --
发表时间: 2003
期刊: Proc.of 3^<rd> POSTECH-KYUTECH Joint Workshop on Neuroinformatics
影响因子: --
作者: [Minatohara, T., Nakamura, Y., Nakabe, T., Yasui, S.]
通讯作者: S.
Modular network SOM : Extension of SOM to the realm of function space.
模块化网络SOM:SOM向功能空间领域的扩展。
DOI: --
发表时间: 2003
期刊: Proc.of Workshop on Soft-Organizing Maps(WSOM'03)
影响因子: --
作者: [Tokunaga, K., Furukawa, T., Yasui, S.]
通讯作者: S.
徳永憲洋: "ベクトル空間でなく関数空間における自己組織化マップ"日本神経回路学会第13回全国大会講演論文集. 124-125 (2003)
Norihiro Tokunaga:“函数空间中的自组织映射而不是向量空间”日本神经网络学会第 13 届全国会议记录 124-125 (2003)。
DOI: --
发表时间:
期刊:
影响因子: --
作者: []
通讯作者:
共 52 条
    Analogical Learning / Inference / Reasoning: A study based on Neural-Network Ideas and Cognitive Science
    • 批准号:
      12680390
    • 项目类别:
      Grant-in-Aid for Scientific Research (C)
    • 资助金额:
      $1.92万
    • 财政年份:
      2000
    • 负责人:
      YASUI Syozo
    • 依托单位:
    A study on synaptic mechanisms in the retinal neural network
    • 批准号:
      06044181
    • 项目类别:
      Grant-in-Aid for international Scientific Research
    • 资助金额:
      $6.98万
    • 财政年份:
      1994
    • 负责人:
      YASUI Syozo
    • 依托单位:
    Exploration of plasticity visual physiologic functions by simultaneous studies on artificial neural networks and vertebrate retina
    • 批准号:
      05452404
    • 项目类别:
      Grant-in-Aid for General Scientific Research (B)
    • 资助金额:
      $3.46万
    • 财政年份:
      1993
    • 负责人:
      YASUI Syozo
    • 依托单位:
    Synaptic Plasticity of Retinal Neurones
    • 批准号:
      05044216
    • 项目类别:
      Grant-in-Aid for Overseas Scientific Survey.
    • 资助金额:
      $0.0万
    • 财政年份:
      1993
    • 负责人:
      YASUI Syozo
    • 依托单位:
    国内基金
    海外基金
    Scalable Learning and Optimization: High-dimensional Models and Online Decision-Making Strategies for Big Data Analysis
    Understanding structural evolution of galaxies with machine learning
    • 批准号:
    • 项目类别:
      省市级项目
    • 资助金额:
      10.0万元
    • 批准年份:
      2022
    • 负责人:
      Nicola Rosario Napolitano
    • 依托单位:
    煤矿安全人机混合群智感知任务的约束动态多目标Q-learning进化分配
    • 批准号:
      --
    • 项目类别:
      青年科学基金项目
    • 资助金额:
      30万元
    • 批准年份:
      2022
    • 负责人:
      吉建娇
    • 依托单位:
    基于领弹失效考量的智能弹药编队短时在线Q-learning协同控制机理
    • 批准号:
      62003314
    • 项目类别:
      青年科学基金项目
    • 资助金额:
      24.0万元
    • 批准年份:
      2020
    • 负责人:
      沈剑
    • 依托单位: