首页> 外文会议>Machine learning >Recognition and Exploitation of Contextual Clues via Incremental Meta-Learning
【24h】

Recognition and Exploitation of Contextual Clues via Incremental Meta-Learning

机译:通过增量元学习识别和利用上下文线索

获取原文
获取原文并翻译 | 示例

摘要

Daily experience shows that in the real world, the meaning or appearance of many concepts heavily depends on some implicit context, and changes in that context can cause more or less radical changes in the concepts. Incremental concept learning in such domains requires the ability to recognize and adapt to such changes. This paper presents a solution for incremental learning tasks where the domain provides explicit clues as to the current context (e.g., attributes with characteristic values). We present a general two-level learning model, and its realization in a system named MetaL(B), that can learn to detect certain types of contextual clues and can react accordingly when a context change is suspected. Context learning and detection occur during regular on-line learning, without separate training phases for context recognition. Experiments with synthetic domains as well as a 'real-world' problem show that MetaL(B) is robust in a variety of dimensions and produces substantial improvement in situations with changing contexts.
机译:日常经验表明,在现实世界中,许多概念的含义或外观在很大程度上取决于某些隐式上下文,并且该上下文中的更改可能会导致或多或少地引起概念上的根本性更改。在此类领域中的增量概念学习需要具备识别并适应此类变化的能力。本文为增量学习任务提供了一种解决方案,其中领域提供了有关当前上下文的明确线索(例如具有特征值的属性)。我们提出了一个通用的两级学习模型,及其在名为MetaL(B)的系统中的实现,该模型可以学习检测特定类型的上下文线索,并且在怀疑上下文更改时可以做出相应的反应。上下文学习和检测发生在常规的在线学习期间,而没有用于上下文识别的单独训练阶段。对合成域以及“现实世界”问题进行的实验表明,MetaL(B)在各种维度上都具有鲁棒性,并且在上下文变化的情况下可以产生实质性的改进。

著录项

  • 来源
    《Machine learning》|1996年|525-533|共9页
  • 会议地点 Bari(IT);Bari(IT)
  • 作者

    Gerhard Widmer;

  • 作者单位

    Dept. of Medical Cybernetics and Artificial Intelligence, University of Vienna, Austria;

  • 会议组织
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 计算机的应用;
  • 关键词

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱:kefu@zhangqiaokeyan.com

京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有
  • 客服微信

  • 服务号