Autonomous systems with explanatory internal models

具有解释性内部模型的自治系统

基本信息

  • 批准号:
    10650434
  • 负责人:
  • 金额:
    $ 1.92万
  • 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:
    1998
  • 资助国家:
    日本
  • 起止时间:
    1998 至 1999
  • 项目状态:
    已结题

项目摘要

Autonomous systems with internal models requires learning algorithms based on variety of trials, methods for extracting general knowledge out of trained results, and hierarchical control structure and its switching mechanisms. To meet these requisites, the following have been studied.As a tool for learning based on variety of trials, the following have been devised : a control mechanism of chaotic behaviors which can produce non-deterministic trials, an optimization method which controls the search range as required, genetic symbiosis algorithm that finds various(sub-)optimal solutions with desirable features, and an optimization procedure that tunes its own design parameters. Their validity has been examined by examples.To achieve extraction of general knowledge, the following have been proposed : neural networks with input gates and a method to merge nodes in Radial Basis Function networks. These enables us to represent the knowledge in a generally applicable way which has a fewer number of inputs(conditions). This has been verfied through learning of behaviors of autonomous moving agents.Neural networks with node gates have been also devised which can realize hierarchical control structure as well as its switching mechanism at the same time. This has been confirmed by examples of nonlinear system control. In addition, in learning of behaviors of autonomous moving agents, a mechanism has been added that extract rules applicable to general environments to are. This makes it possible for the agents to adapt new environment more quickly, which has been demonstrated in examples.
具有内部模型的自治系统需要基于各种试验的学习算法、从训练结果中提取一般知识的方法以及递阶控制结构及其切换机制。作为一种基于各种试验的学习工具,设计了一种可以产生非确定性试验的混沌行为的控制机制,一种根据需要控制搜索范围的优化方法,一种找到具有期望特征的各种(次)最优解的遗传共生算法,以及一种自适应调整设计参数的优化过程。为了实现一般知识的提取,提出了带输入门的神经网络和径向基函数网络中节点合并的方法。这些使我们能够以一种具有较少输入(条件)的普遍适用的方式来表示知识。通过对自主移动智能体行为的学习验证了这一点,并设计了带节点门的神经网络,同时实现了递阶控制结构及其切换机制。这一点已被非线性系统控制的实例所证实。此外,在自主移动代理的行为学习中,增加了一种提取适用于一般环境的规则的机制。这使得代理可以更快地适应新的环境,这在示例中已经得到了证明。

项目成果

期刊论文数量(35)
专著数量(0)
科研奖励数量(0)
会议论文数量(0)
专利数量(0)
"Chaos Control Using Maximum Lyapunov Number of Universal Learning Network"Proceedings of 1998 IEEE International Conference on Systems, Man, and Cybernetics. 1702-1707 (1998)
“利用通用学习网络的最大李雅普诺夫数进行混沌控制”1998 年 IEEE 国际系统、人与控制论会议论文集。
  • DOI:
  • 发表时间:
  • 期刊:
  • 影响因子:
    0
  • 作者:
  • 通讯作者:
K. Hirasawa: "'Chaos Control Using Maximum Lyapunov Number of Universal Learning Network'"Proceedings of 1998 IEEE International Conference on Systems, Man, and Cybernetics. 1702-1707 (1998)
K. Hirasawa:“‘利用通用学习网络的最大李雅普诺夫数进行混沌控制’”1998 年 IEEE 国际系统、人类和控制论会议记录。
  • DOI:
  • 发表时间:
  • 期刊:
  • 影响因子:
    0
  • 作者:
  • 通讯作者:
片桐広伸: "Dynamics of multi-agent systems by RasID Learning"Proceedings of 1999 IEEE International Conference on Systems, Man, and Cybernetics. Vol.1. 233-238 (1999)
Hironobu Katagiri:“RasID 学习的多智能体系统动力学”1999 年 IEEE 国际系统、人类和控制论会议论文集,第 1 卷(1999 年)。
  • DOI:
  • 发表时间:
  • 期刊:
  • 影响因子:
    0
  • 作者:
  • 通讯作者:
"Training Neural Networks Based on Random Searching Scheme"Proceedings of International Conference on Artifical Intelligence for Engineering. 298-302 (1998)
“基于随机搜索方案的训练神经网络”工程人工智能国际会议论文集。
  • DOI:
  • 发表时间:
  • 期刊:
  • 影响因子:
    0
  • 作者:
  • 通讯作者:
胡 敬炉: "RasID-Random Search for Neutal Networks Training" Journal of Advanced Computational Intelligence. 2・4. 134-141 (1998)
胡经洛:“RasID-神经网络训练的随机搜索”《高级计算智能》杂志 2・4(1998)。
  • 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 }}

MURATA Junichi其他文献

MURATA Junichi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('MURATA Junichi', 18)}}的其他基金

The problem of free will in the contemporary situation: toward the unification of theoretical and practical considerations
当代形势下的自由意志问题:走向理论与实践的统一
  • 批准号:
    25370031
  • 财政年份:
    2013
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Solution of multistage decision problems considering subjectively evaluated risks of changes in problems
考虑问题变化的主观评估风险的多阶段决策问题的解决
  • 批准号:
    24560499
  • 财政年份:
    2012
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Ecological Phenomenology and the Philosophy of Technology: Toward a construction of appropriate environments from an ecological point of view
生态现象学与技术哲学:从生态角度构建适当的环境
  • 批准号:
    21320003
  • 财政年份:
    2009
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (B)
Solution and applications of multi-objective optimization problems with distributed multiple evaluators
分布式多评价器多目标优化问题的求解及应用
  • 批准号:
    20560386
  • 财政年份:
    2008
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Sensation・Perception・Conception--the possibility of "ecological phenomenology " of perception
感觉・知觉・构想--知觉“生态现象学”的可能性
  • 批准号:
    18520004
  • 财政年份:
    2006
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
The significance and the scope of the "inessentialism" in the philosophy of technology
技术哲学中“非本质主义”的意义和范围
  • 批准号:
    13610004
  • 财政年份:
    2001
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
The Consciousness-the science and phenomenology about it
意识——有关它的科学和现象学
  • 批准号:
    10610006
  • 财政年份:
    1998
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
The Possibility and the Necessity of the phenomenological point of view in the Philosophy of Technology
技术哲学中现象学观点的可能性与必要性
  • 批准号:
    08610006
  • 财政年份:
    1996
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Self-Constructing Systems and their Applications to System Identification and Control
自构建系统及其在系统辨识与控制中的应用
  • 批准号:
    07650499
  • 财政年份:
    1995
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for Scientific Research (C)
Early Phenomenology--Brentanno school and Husserl
早期现象学——布伦坦诺学派与胡塞尔
  • 批准号:
    05610002
  • 财政年份:
    1993
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Grant-in-Aid for General Scientific Research (C)

相似国自然基金

Scalable Learning and Optimization: High-dimensional Models and Online Decision-Making Strategies for Big Data Analysis
  • 批准号:
  • 批准年份:
    2024
  • 资助金额:
    万元
  • 项目类别:
    合作创新研究团队
供应链管理中的稳健型(Robust)策略分析和稳健型优化(Robust Optimization )方法研究
  • 批准号:
    70601028
  • 批准年份:
    2006
  • 资助金额:
    7.0 万元
  • 项目类别:
    青年科学基金项目

相似海外基金

CAREER: Resilient and Efficient Automatic Control in Energy Infrastructure: An Expert-Guided Policy Optimization Framework
职业:能源基础设施中的弹性和高效自动控制:专家指导的政策优化框架
  • 批准号:
    2338559
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Standard Grant
CAREER: From Dynamic Algorithms to Fast Optimization and Back
职业:从动态算法到快速优化并返回
  • 批准号:
    2338816
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Continuing Grant
CAREER: Structured Minimax Optimization: Theory, Algorithms, and Applications in Robust Learning
职业:结构化极小极大优化:稳健学习中的理论、算法和应用
  • 批准号:
    2338846
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Continuing Grant
Planning: Artificial Intelligence Assisted High-Performance Parallel Computing for Power System Optimization
规划:人工智能辅助高性能并行计算电力系统优化
  • 批准号:
    2414141
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Standard Grant
CAS: Optimization of CO2 to Methanol Production through Rapid Nanoparticle Synthesis Utilizing MOF Thin Films and Mechanistic Studies.
CAS:利用 MOF 薄膜和机理研究,通过快速纳米粒子合成优化 CO2 生产甲醇。
  • 批准号:
    2349338
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Continuing Grant
Collaborative Research: An Integrated Framework for Learning-Enabled and Communication-Aware Hierarchical Distributed Optimization
协作研究:支持学习和通信感知的分层分布式优化的集成框架
  • 批准号:
    2331710
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Standard Grant
Collaborative Research: An Integrated Framework for Learning-Enabled and Communication-Aware Hierarchical Distributed Optimization
协作研究:支持学习和通信感知的分层分布式优化的集成框架
  • 批准号:
    2331711
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Standard Grant
CAREER: Mitigating the Lack of Labeled Training Data in Machine Learning Based on Multi-level Optimization
职业:基于多级优化缓解机器学习中标记训练数据的缺乏
  • 批准号:
    2339216
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Continuing Grant
Real Versus Digital: Sustainability optimization for cultural heritage preservation in national libraries
真实与数字:国家图书馆文化遗产保护的可持续性优化
  • 批准号:
    AH/Z000041/1
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Research Grant
Collaborative Research: SaTC: CORE: Medium: Differentially Private SQL with flexible privacy modeling, machine-checked system design, and accuracy optimization
协作研究:SaTC:核心:中:具有灵活隐私建模、机器检查系统设计和准确性优化的差异化私有 SQL
  • 批准号:
    2317232
  • 财政年份:
    2024
  • 资助金额:
    $ 1.92万
  • 项目类别:
    Continuing Grant
{{ showInfoDetail.title }}

作者:{{ showInfoDetail.author }}

知道了