课题基金 / 基金详情

Integrating Explanation-Based and Neural Approaches to Machine Learning

Integrating Explanation-Based and Neural Approaches to Machine Learning
将基于解释的方法和神经方法集成到机器学习中
批准号:
9002413
负责人:
Jude Shavlik
金额:
$17.01万
依托单位国家:
美国
项目类别:
Continuing Grant
财政年份:
1990
资助国家:
美国
项目状态:
已结题
起止时间:
1990-09-01 至 1994-08-31

项目摘要

项目成果

Jude Shavlik的其他基金

相似基金

相关文献

中文摘要
翻译
要被认为是智能的,机器必须有学习的能力。对机器学习的符号方法和神经方法都进行了大量研究。然而,关于将这两种学习范式结合起来所能实现的协同效应的研究很少。这项工作将开发一个混合系统,将基于符号的解释学习范式与神经反向传播算法相结合。在该系统中,初始神经网络的配置由对特定类别的计划任务的解的广义解释来确定。这项研究解决了选择一个好的初始神经网络结构的问题,并克服了使用不完善的理论建立解释时出现的问题。大多数现实世界的问题永远不可能被完全形式化。然而,利用这种能力进行大致正确的推理将会有很大的好处。基于解释的学习提供了一种有利可图地使用随意世界模型的方法,而神经网络提供了一种提炼大致正确的概念的方法。这项将这两种学习范式结合在一起的研究有望扩大机器学习技术的适用性,产生不脆弱的学习算法,并能够产生通过经验提高精度的概念。
英文摘要
To be considered intelligent, machines must be capable of learning. Symbolic and neural approaches to machine learning both have been heavily investigated. However, there has been little research into the synergies achievable by combining these two learning paradigms. This work will develop a hybrid system that combines the symbolically-oriented explanation-based learning paradigm with the neural back-propagation algorithm. In this system, the initial neural network configuration is determined by the generalized explanation of the solution to a specific classification of planning task. This research addresses the problem of choosing a good initial neural network configuration and overcomes problems that arise when using imperfect theories to build explanations. Most real-world problems can never be formalized exactly. However, there is much to be gained by utilizing the capability to reason approximately correctly. Explanation-based learning provides a way to profitably use casual models of the world, while neural networks provide a way to refine roughly-correct concepts. This research on combining these two learning paradigms promises to broaden the applicability of machine learning techniques, producing learning algorithms that are not brittle and which can produce concepts whose accuracy improves through experience.
期刊论文(0)
专著(0)
科研奖励(0)
会议论文
Learning from Instruction and Experience
  • 批准号:
    9502990
  • 项目类别:
    Continuing Grant
  • 资助金额:
    $45.61万
  • 财政年份:
    1996
  • 负责人:
    Jude Shavlik
  • 依托单位:
国内基金
海外基金
Exploring the Intrinsic Mechanisms of CEO Turnover and Market Reaction: An Explanation Based on Information Asymmetry
  • 批准号:
    W2433169
  • 项目类别:
    外国学者研究基金项目
  • 资助金额:
    --
  • 批准年份:
    2024
  • 负责人:
    HAOFEI ZHANG
  • 依托单位: