首页> 外文会议>2001 IEEE/RSJ International Conference on Intelligent Robots and Systems, 2001. Proceedings, 2001 >A system extending backpropagation to learnclassification/categorization without a teacher, form a small basis forlarger knowledge structures, and make additional reasoning usingknowledge learned from classification/categorization
【24h】

A system extending backpropagation to learnclassification/categorization without a teacher, form a small basis forlarger knowledge structures, and make additional reasoning usingknowledge learned from classification/categorization

机译:一种将反向传播扩展到无需教师的学习分类/分类的系统,为较大的知识结构奠定了很小的基础,并使用从分类/分类中学习的知识进行其他推理

获取原文
获取原文并翻译 | 示例

摘要

Summary form only given. The author briefly reviewsnbackpropagation and points out in detail the problems and issues relatednto it. Then he examines a method that will help alleviate some of thesenproblems, all within the same system. Although the system is explainednpart by part, the small contribution of this study is perhaps not howneach specific part solves a problem, but how the various pieces of thenresulting system fit together to alleviate some of those problems withinnthe same system. In addition, the author examines some of the issuesnrelated to the resulting method
机译:仅提供摘要表格。作者简要回顾了反向传播,并详细指出了与之相关的问题。然后,他研究了一种方法,该方法将帮助缓解某些问题,所有这些问题都在同一系统中。尽管对系统进行了部分解释,但本研究的微小贡献也许不是如何解决特定部分的问题,而是如何将结果系统的各个部分组合在一起以缓解同一系统中的某些问题。此外,作者研究了与结果方法相关的一些问题

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