• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Intelligent Agents, 2009. IA '09 >Learning by teaching versus learning by doing: Knowledge exchange in organic agent systems
【24h】

Learning by teaching versus learning by doing: Knowledge exchange in organic agent systems

机译：边教边学：边做边学：有机代理系统中的知识交换

获取原文
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

ldquoLearning by doingrdquo and ldquolearning by teachingrdquo are two important concepts for human education. In this article, we demonstrate that these learning concepts can also be realized by intelligent, so-called organic computing systems. These organic agents either improve their skills by themselves, eventually assisted by a teacher, or they teach each other by exchanging learned rules. We show that ldquolearning by teachingrdquo may reduce the query costs for teachers and allow for a proactive behavior of organic agents: Before certain situations emerge in their environment, they are already enabled to deal with that situations. We also show that ldquolearning by teachingrdquo may be problematic in cases where different agents are expected to have-at least partiallyldquodifferent skills. Then, incautious knowledge exchange may yield a performance degradation. There are many possible application fields for these organic systems, e.g., distributed intrusion detection, robotics, or sensor networks.
机译：“边做边学”和“边教边学”是人类教育的两个重要概念。在本文中，我们证明了这些学习概念也可以通过智能的所谓有机计算系统来实现。这些有机的代理人要么自己提高技能，最后在老师的帮助下，要么通过交流学到的规则互相教书。我们表明，通过教学进行“学习”可以减少教师的查询成本，并允许有机代理主动行为：在某些情况出现在他们的环境中之前，他们已经能够处理这种情况。我们还表明，在期望不同的代理至少具有部分“不同”技能的情况下，通过“教学”学习可能会出现问题。然后，不适当的知识交流可能会导致性能下降。这些有机系统有许多可能的应用领域，例如分布式入侵检测，机器人技术或传感器网络。

著录项

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