Autoeoncoders and Information Augmentation for Improved Generalization and Interpretation in Multi-layered Neural Networks
Autoeoncoders and Information Augmentation for Improved Generalization and Interpretation in Multi-layered Neural Networks
复制标题
DOI：
10.1109/iscbi.2018.00020
复制
发表时间：
2018-08
期刊：
影响因子：
--
通讯作者：
R. Kamimura
中科院分区：
文献类型：
--
作者：
R. Kamimura
针对多层神经网络的信息消失问题，提出了一种新的学习方法。消失信息问题意味着多层神经网络往往会通过许多隐藏层丢失其错误信息以及输入信息。为了克服这个问题，新方法试图通过增加输入的数量，产生复合输入变量来尽可能多地捕获输入中的信息。将该方法应用于对称数据集和葡萄酒数据集。对于对称数据集，新方法能够更好地捕捉输入数据集的对称性，具有更好的泛化性能。对于葡萄酒数据集，新方法可以捕获组合特征检测的装袋方法和逻辑回归分析具有更好的泛化性能。
The present paper aims to propose a new type of learning method for multi-layered neural network to solve the vanishing information problem. The vanishing information problem means that multi-layered neural networks tend to lose their error information as well as input information by going through many hidden layers. To overcome this problem, the new method tries to capture information in inputs as much as possible by increasing the number of inputs, producing composite input variables. The new method was applied to the symmetric data set and wine data sets. For the symmetric data set, the new method could capture the symmetric property of input data set with better generalization performance. For the wine data set, the new method could capture combined characteristics detected by the bagging method and logistic regression analysis with better generalization performance.