| 基于CUDA和深度置信网络的手写字符识别 |
| |
| 引用本文： | 陆军建,林家骏.基于CUDA和深度置信网络的手写字符识别[J].医学教育探索,2015(2):210-215. |
| |
| 作者姓名： | 陆军建 林家骏 |
| |
| 作者单位： | 华东理工大学化工过程先进控制和优化技术教育部重点实验室，上海 200237,华东理工大学化工过程先进控制和优化技术教育部重点实验室，上海 200237 |
| |
| 摘 要： | 为了应对海量的字符(手写)识别，提出了一种将统一计算设备架构 (Compute Unified Device Architecture, CUDA)和深度置信网络相结合的方法进行手写字符识别。该方法结合受限玻尔兹曼机和反向传播神经网络形成深度置信网络对字符图片数据进行识别，并且使用CUDA在图形处理器（GPU）上进行并行计算来完成识别过程。实验结果表明，使用该方法后，在不降低识别精度的情况下手写字符识别的速度大幅提升。
|
| 关 键 词： | GPU CUDA 手写字符识别 深度置信网络 |
| 收稿时间： | 2014/6/23 0:00:00 |
Handwritten Character Recognition Based on CUDA and Deep Belief Networks |
| |
| LU Jun-jian and LIN Jia-jun.Handwritten Character Recognition Based on CUDA and Deep Belief Networks[J].Researches in Medical Education,2015(2):210-215. |
| |
| Authors: | LU Jun-jian and LIN Jia-jun |
| |
| Institution: | Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China and Key Laboratory of Advanced Control and Optimization for Chemical Processes, Ministry of Education, East China University of Science and Technology, Shanghai 200237, China |
| |
| Abstract: | By combining Compute Unified Device Architecture (CUDA) and Deep Belief Network (DBN), this paper proposes a method to handle the recognition of massive handwritten characters. This method integrates Restricted Boltzmann Machine (RBM) and back propagation neural network to forming a DBN to recognize the characters. Moreover, the concurrent computation of CUDA is made in GPU to achieve the recognition. The results show that the proposed method can significantly improve the speed of recognition on handwritten characters without reducing the accuracy of recognition. |
| |
| Keywords: | GPU CUDA handwritten character recognition Deep Belief Networks |
|
| 点击此处可从《医学教育探索》浏览原始摘要信息 |
| 点击此处可从《医学教育探索》下载免费的PDF全文 |
