桂林电子科技大学学报2017，Vol.37Issue(3)：197-202,6.
基于最大相关熵的自编码网络人脸识别
Face recognition method based on auto-encoder network with maximum correlation entropy
摘要
Abstract
To overcome the problem of noise in the auto-encoder network and its variants where mean square error is regard as reconstruction function,a stacked sparse auto-encoder network is proposed,the maximum relative entropy is used as the reconstruction function of network and a multi-layer network with sparse constraint is constructed in the method.Experimental results demonstrate that the proposed method is more robustness than the traditional auto-encoder network on the YaleB and AR databases whether the training samples are noisy or not noisy.In addition,it achieves better recognition performance and the learned features are more powerful.关键词
自编码网络/均方误差/最大相关熵/稀疏约束项/鲁棒性Key words
auto-encoder network/mean square error/maximum correlation entropy/sparse constraint/robustness分类
信息技术与安全科学引用本文复制引用
匡勇建,莫建文,张顺岚..基于最大相关熵的自编码网络人脸识别[J].桂林电子科技大学学报,2017,37(3):197-202,6.基金项目
国家自然科学基金(61362021,61661017) （61362021,61661017）
广西自然科学基金(2014GXNSFDA118035) （2014GXNSFDA118035）
桂林电子科技大学研究生教育创新计划(YJCX201534) （YJCX201534）
