• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Weight decay training, fuzzy set techniques, and rule extraction for backpropagation: Learning from incomplete and imprecise data.
【24h】

Weight decay training, fuzzy set techniques, and rule extraction for backpropagation: Learning from incomplete and imprecise data.

机译：权重衰减训练，模糊集技术和用于反向传播的规则提取：从不完整和不精确的数据中学习。

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

The major purpose of this thesis is to improve the backpropagation learning algorithm in the following aspects: (1) Apply weight decay training to improve performance for undersized or oversized networks; (2) Apply fuzzy set techniques to determine learning rates; (3) Apply rule extraction to explain training results; (4) Apply backpropagation for reconstruction of missing values; (5) Apply weight decay backpropagation to learning from noisy data; and (6) Apply fuzzy set techniques to learning from borderline cases.;Experimental results confirm the superiority of weight decay training over standard backpropagation regardless of network architectures. The proposed RE algorithm provides a viable technique for extracting rules from a feedforward network trained using backpropagation. The RE algorithm has several advantages: (1) Classification rules from RE are highly tractable and interpretable; (2) RE is computationally efficient; (3) RE does not require domain knowledge; and (4) As RE utilizes both the strengths of connection weights and the activation levels of hidden nodes for rule extraction, it avoids the problem of tampering with the learning process caused by converting the sigmoid function into a step function.;Fuzzy set techniques are applied to determine the backpropagated errors and the learning rate for each input pattern based on its class membership values. The technique of variable learning rate is extended from two-class problems to multi-class problems. Borderline cases are technically defined using the standard deviations of class membership values. Fuzzy set techniques are shown to be effective in improving correct classification rates for data sets with high percentages of borderline cases as well as cases with compatible given crisp targets and fuzzy class membership values.;The standard backpropagation algorithm outperforms other statistical techniques for reconstruction of missing values. Moreover, reconstructed data has a positive effect on improving correct classification rates. The percentage of missing values has greater differential effect on reconstruction and classification methods than the randomness of missing values does. For noisy data, experimental results suggest: (1) Weight decay training achieves correct classification rates better than or equivalent to standard backpropagation; (2) Weight decay training tends to require fewer training epochs than standard backpropagation to converge; and (3) Noise in future cases deteriorates correct classification rates more significantly than noise in training cases does for backpropagation training.
机译：本文的主要目的是从以下几个方面改进反向传播学习算法：（1）运用权重衰减训练来提高网络规模过大或过大的性能； （2）运用模糊集技术确定学习率； （3）应用规则提取来解释训练结果； （4）应用反向传播重建缺失值； （5）将权重衰减反向传播应用于从噪声数据中学习； （6）应用模糊集技术从临界情况中学习。实验结果证实了重量衰减训练优于标准反向传播的优势，而与网络架构无关。提出的RE算法为从使用反向传播训练的前馈网络提取规则提供了一种可行的技术。 RE算法具有以下优点：（1）RE的分类规则易于处理和解释； （2）RE具有计算效率； （3）RE不需要领域知识； （4）由于RE利用连接权重的强度和隐藏节点的激活水平来进行规则提取，因此避免了由于将S形函数转换为阶跃函数而造成的学习过程篡改的问题。用于基于其类成员值确定每个输入模式的反向传播错误和学习率。可变学习率的技术从两类问题扩展到多类问题。临界情况是使用类成员资格值的标准偏差在技术上定义的。事实证明，模糊集技术可以有效提高边缘案例百分比高以及具有给定清晰目标和模糊类隶属度值的情况下的数据集的正确分类率。;标准反向传播算法在重建缺失方面优于其他统计技术价值观。而且，重建的数据对提高正确的分类率具有积极的作用。与缺失值的随机性相比，缺失值的百分比对重构和分类方法的影响更大。对于嘈杂的数据，实验结果表明：（1）重量衰减训练获得的正确分类率优于或等于标准反向传播； （2）重量衰减训练趋向于比标准反向传播收敛所需的训练时期更少； （3）与反向传播训练中训练案例中的噪声相比，未来案例中的噪声对正确分类率的破坏更为严重。

著录项

  • 作者

    Lam, Siuwa Monica.;

  • 作者单位

    The University of Wisconsin - Madison.;

  • 授予单位 The University of Wisconsin - Madison.;
  • 学科 Information science.;Business education.;Computer science.;Artificial intelligence.
  • 学位 Ph.D.
  • 年度 1994
  • 页码 330 p.
  • 总页数 330
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 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