.png){kind=icon}
返回
A convolutional recursive modified Self Organizing Map for handwritten digits recognition
.png){kind=icon}
PRE
AI
DOI：10.1016/j.neunet.2014.08.001.png)
.png){kind=icon}
原文求助.png){kind=icon}
分享.png){kind=icon}
收藏
摘要
En 中文
It is well known that the handwritten digits recognition is a challenging problem. Different classification algorithms have been applied to solve it. Among them, the Self Organizing Maps (SUM) produced promising results. In this paper, first we introduce a Modified SUM for the vector quantization problem with improved initialization process and topology preservation. Then we develop a Convolutional Recursive Modified SUM and apply it to the problem of handwritten digits recognition. The computational results obtained using the well known MNIST dataset demonstrate the superiority of the proposed algorithm over the existing SUM-based algorithms. (C) 2014 Elsevier Ltd. All rights reserved.
Keyword:
Self Organizing Maps
Vector quantization
SUM initialization
SUM topology
Recursive neural network
Convolutional neural network
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:
6.3
论文数:
8.3K
被引数:
3.0W
机构
引用论文
Discriminative structure selection method of Gaussian Mixture Models with its application to handwritten digit recognition.png)
NEUROCOMPUTING
NEUROCOMPUTINGIF6.5
PREAI
分享收藏Large-scale data exploration with the hierarchically growing hyperbolic SOMNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏分享收藏Investigation of efficient features for image recognition by neural networksNEURAL NETWORKS
NEURAL NETWORKSIF6.3
PREAI
分享收藏A statistical-topological feature combination for recognition of handwritten numerals用于识别手写数字的统计拓扑特征组合
PREAI
分享收藏
查看更多内容