| 基于自编码神经网络建立的搜索信息模型 |
 点此下载全文 |
| 引用本文：易万,罗晶，李勇，郭少英.基于自编码神经网络建立的搜索信息模型[J].计算技术与自动化,2015,(2):117-121 |
| 摘要点击次数: 1209 |
| 全文下载次数: 65 |
|
|
| 中文摘要:根据用户搜索历史，将用户关注的信息按标题分类，通过自编码神经网络提取特征值。设定学习样本标题最多为25个汉字，编码方式采用汉字机内码(GBK码)。使用MATLAB工具进行深度学习，将样本在原空间的特征表示变换到一个新的特征空间。 |
| 中文关键词:文本特征 自编码神经网络 深度学习 Matlab |
| |
| Information Search Model Based on Auto-encoder Neural Network |
|
|
| Abstract:According to user search history, the user information of interest was classified by Title, from which the feature value was extracted by the auto-encoder neural network. The method set the learning sample heading up to 25 Chinese characters, adopted Chinese characters machine code (GBK code) to realize coding mode, used the MATLAB tool for deep learning, and transformed the feature in the original space representation into a new feature space. |
| keywords:text feature the auto-encoder neural network deep learning Matlab |
| 查看全文 查看/发表评论 下载pdf阅读器 |
次