• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文会议>Discovery science >Recursive Extraction of Modular Structure from Layered Neural Networks Using Variational Bayes Method
【24h】

Recursive Extraction of Modular Structure from Layered Neural Networks Using Variational Bayes Method

机译：变分贝叶斯方法从分层神经网络递归提取模块结构

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

Deep neural networks have made a substantial contribution to the recognition and prediction of complex data in various fields, such as image processing, speech recognition and bioinformatics. However, it is very difficult to discover knowledge from the inference provided by a neural network, since its internal representation consists of many nonlinear and hierarchical parameters. To solve this problem, an approach has been proposed that extracts a global and simplified structure for a neural network. Although it can successfully detect such a hidden modular structure, its convergence is not sufficiently stable and is vulnerable to the initial parameters. In this paper, we propose a new deep learning algorithm that consists of recursive back propagation, community detection using a variational Bayes, and pruning unnecessary connections. We show that the proposed method can appropriately detect a hidden inference structure and compress a neural network without increasing the generalization error.
机译：深度神经网络为各种领域（例如图像处理，语音识别和生物信息学）中的复杂数据的识别和预测做出了重大贡献。但是，由于神经网络的内部表示由许多非线性和分层参数组成，因此很难从神经网络提供的推论中发现知识。为了解决这个问题，已经提出了一种提取神经网络的全局和简化结构的方法。尽管它可以成功检测到这种隐藏的模块化结构，但其收敛不够稳定，并且容易受到初始参数的影响。在本文中，我们提出了一种新的深度学习算法，该算法包括递归反向传播，使用变分贝叶斯算法进行社区检测以及修剪不必要的连接。我们表明，所提出的方法可以适当地检测隐藏的推理结构并压缩神经网络，而不会增加泛化误差。

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