| 基于自编码神经网络建立的搜索信息模型 |
| |
| 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. |
| |
| 作者姓名： | 易万 罗晶 李勇 郭少英 |
| |
| 作者单位： | 1. 天津科技大学 计算机科学与信息工程学院,天津,300222
2. 天津科技大学 生物工程学院,天津,300457 |
| |
| 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。
|
| 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 |
| |
| YI Wan,LUO Jing,LI Yong,GUO Shao-ying.Information Search Model Based on Auto-encoder Neural Network[J].Computing Technology and Automation,2015(2):117-121. |
| |
| Authors: | YI Wan LUO Jing LI Yong GUO Shao-ying |
| |
| Affiliation: | (1.College of computer science and Information Engineering, Tianjin University of Science & Technology,Tianjin300222,China;2.Institute of Biological Engineering,Tianjin University of Sciemce & Technology,Tianjin300457,China) |
| |
| 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 |
| 本文献已被 万方数据 等数据库收录！ |
| 点击此处可从《计算技术与自动化》浏览原始摘要信息 |
|
点击此处可从《计算技术与自动化》下载全文 |
|
