• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文期刊>Neural Networks and Learning Systems, IEEE Transactions on >Deep Learning of Constrained Autoencoders for Enhanced Understanding of Data
【24h】

Deep Learning of Constrained Autoencoders for Enhanced Understanding of Data

机译：深度学习约束自动编码器以增强对数据的理解

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

Unsupervised feature extractors are known to perform an efficient and discriminative representation of data. Insight into the mappings they perform and human ability to understand them, however, remain very limited. This is especially prominent when multilayer deep learning architectures are used. This paper demonstrates how to remove these bottlenecks within the architecture of non-negativity constrained autoencoder. It is shown that using both L1 and L2 regularizations that induce non-negativity of weights, most of the weights in the network become constrained to be non-negative, thereby resulting into a more understandable structure with minute deterioration in classification accuracy. Also, this proposed approach extracts features that are more sparse and produces additional output layer sparsification. The method is analyzed for accuracy and feature interpretation on the MNIST data, the NORB normalized uniform object data, and the Reuters text categorization data set.
机译：已知无监督的特征提取器可以执行高效且有区别的数据表示。然而，对它们执行的映射的洞察力以及人类对其理解的能力仍然非常有限。当使用多层深度学习架构时，这一点尤其突出。本文演示了如何消除非负约束自动编码器体系结构中的这些瓶颈。结果表明，使用导致权重非负的L1和L2正则化，网络中的大多数权重都被约束为非负，从而导致结构更易于理解，并且分类精度稍有下降。同样，此提议的方法提取的特征更加稀疏，并产生额外的输出层稀疏性。分析了该方法的准确性和特征解释，包括MNIST数据，NORB归一化的统一对象数据和Reuters文本分类数据集。

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