基于梯度的多输入卷积神经网络  

Multi-input Convolutional Neural Network Based on Gradient

作　　者：费建超 芮挺[1] 周遊[2] 方虎生[1] 朱会杰[1] 

机构地区：[1]解放军理工大学野战工程学院,南京210007 [2]江苏经贸职业技术学院,南京210007

出　　处：《光电工程》2015年第3期33-38,共6页Opto-Electronic Engineering

基　　金：国家自然科学基金(61472444;61472392)资助项目

摘　　要：深度学习已成为目前机器学习领域的研究热点,卷积神经网络是深度学习的重要组成。以卷积神经网络为基础,结合自动编码提取特征中的边缘特性,采用多方向梯度信息作为边缘信息的基本表达,并以此作为卷积神经网络的多源输入数据,提出了一种具有多个输入层的卷积神经网络结构。以手写字符识别和行人检测为例,通过实验表明,梯度信息多输入网络与经典卷积神经网络相比,具有更高的识别率,且在训练次数少的情况下优势更为明显,同时也证明在适度预处理的条件下多输入卷积神经网络能够获得更好的效果。Deep learning has been a hot spot in the area of machine learning, of which the convolutional neural network is an important component. Based on the deep convolutional neural network and the edge features of characters extracted by auto-encoder, a convolutional neural network of multi-input layers was proposed, which input layers consisted of multi-input with gradient of various directions. In the experiments of handwritten numbers recognition and pedestrian detection, the multi-input network has higher recognition rate compared with the traditional network structure, especially when the number of training time is fewer. This result also provides a proof that multi-input convolutional neural network performed better with appropriate preprocessing.

关 键 词：深度学习 卷积神经网络 多输入 梯度 

分 类 号：TP139.41[自动化与计算机技术—控制理论与控制工程]