• 主题
高级搜索  >
历史搜索 清空历史
首页> 美国政府科技报告 >Introspective Multistrategy Learning: On the Construction of Learning Strategies
【24h】

Introspective Multistrategy Learning: On the Construction of Learning Strategies

机译：反思性多学科学习：学习策略的构建

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

摘要

A central problem in multistrategy learning systems is the selection and sequencing of machine learning algorithms for particular situations. This is typically done by the system designer, who analyzes the learning task and implements the appropriate algorithm or sequence of algorithms for that task. The authors propose a solution to this problem that enables an Artificial Intelligence (AI) system with a library of machine learning algorithms to select and sequence appropriate algorithms autonomously. Furthermore, instead of relying on the system designer or user to provide a learning goal or target concept to the learning system, this method enables the system to determine its own learning goals based on an analysis of its successes and failures at the performance task. The method involves three steps: Given a performance failure, the learner examines a trace of its reasoning prior to the failure to diagnose what went wrong (blame assignment); given the resultant explanation of the reasoning failure, the learner posts explicitly represented learning goals to change its background knowledge (deciding what to learn); and given a set of learning goals, the learner uses nonlinear planning techniques to assemble a sequence of machine learning algorithms, represented as planning operators, to achieve the learning goals (learning-strategy construction). In support of these operations, the authors define the types of reasoning failures, a taxonomy of failure causes, a second-order formalism to represent reasoning traces, a taxonomy of learning goals that specify desired change to the background knowledge of a system, and a declarative task-formalism representation of learning algorithms. They present the Meta-AQUA system, an implemented multistrategy learner that operates in the domain of story understanding.

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