.png){kind=icon}
返回
Morphological Convolutional Neural Network Architecture for Digit Recognition
.png){kind=icon}
PRE
AI
DOI：10.1109/TNNLS.2018.2890334.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
Deep neural networks have proved promising results in many applications and fields, but they are still assimilated to a black box. Thus, it is very useful to introduce interpretability aspects to prevent the blind application of deep networks. This paper proposed an interpretable morphological convolutional neural network called Morph-CNN for pattern recognition, where morphological operations were incorporated using counter-harmonic mean into the convolutional layer in order to generate enhanced feature maps. Morph-CNN was extensively evaluated on MNIST and SVHN benchmarks for digit recognition. The different tested configurations showed that Morph-CNN outperforms the existing methods.
Keyword:
Convolutional neural network (CNN)
deep neural networks (DNNs)
image recognition
interpretability
morphological CNN (Morph-CNN)
morphological operators
AI总结
对已上传原文的论文进行重点信息的提取，主要内容包括：简要概述、研究摘要、背景介绍、关键亮点、图文解析、展望与总结。
期刊
IF:
8.9
论文数:
7.6K
被引数:
7.2W
机构
引用论文
Nanocomposite of hexagonal β-Ni(OH)2/multiwalled carbon nanotubes as high performance electrode for hybrid supercapacitors六方 β-ni (OH)2/多壁碳纳米管复合材料作为混合超级电容器的高性能电极
PREAI
分享收藏XPS and AES studies of the composition of the viscous liquid film in the electropolishing of copper
PREAI
分享收藏Molecular programming of organogelators which can accept [60]fullerene by encapsulation可以通过封装接受 [60] 富勒烯的有机胶凝剂的分子编程.png)
Tetrahedron
TetrahedronIF0
PREAI
分享收藏Zur Kenntnis der μ‐Peroxo‐bis(pentacyanokobaltate(III)). Neuartige Darstellung, Beschreibung eines μ‐Hydroperoxo‐komplexes K5[Co2OOH(CN)10] · 2 H2O und eines μ‐Peroxo‐Carbonato‐Komplexes K6[Co2CO4(CN)10] · 2 H2OZur Kenntnis der μ-过氧双 (五氰基高钴酸盐 (III))。新的达斯特隆，过氧化氢K5[Co2OOH(CN)10] ·2 h 2O和过氧化氢K6[co 2CO4(CN)10] · 2 H2O
PREAI
分享收藏
查看更多内容