arXivDaily arXiv每日学术速递 周一至周五更新
arXiv周末暂无论文更新,休息一下吧,周末愉快~~
arXiv 1911.07702cs.LGstat.ML
收藏

连体神经网络的一种解释方法

An explanation method for Siamese neural networks

Peter the Great St.Petersburg Polytechnic University (SPbPU)(彼得大帝圣彼得堡理工大学)

Lev V. Utkin, Maxim S. Kovalev, Ernest M. Kasimov

摘要:

提出了一种新的解释连体神经网络的方法。它使用了以下主要思想。首先,将解释的特征向量与在嵌入级计算的对应类的原型(Siamese神经网络输出)进行比较。在这个级别上的重要特征被确定为与原型的相同特征接近的特征。其次,以特殊的方式训练自动编码器,以考虑Si-amese网络的嵌入级别,并且其解码器部分用于重构具有相应变化的输入数据。数值实验与著名的数据集MNIST说明所提出的方法。

英文摘要:

A new method for explaining the Siamese neural network is proposed. It uses the following main ideas. First, the explained feature vector is compared with the prototype of the corresponding class computed at the embedding level (the Siamese neural network output). The important features at this level are determined as features which are close to the same features of the prototype. Second, an autoencoder is trained in a special way in order to take into account the embedding level of the Si-amese network, and its decoder part is used for reconstructing input data with the corresponding changes. Numerical experiments with the well-known dataset MNIST illustrate the propose method.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑