电子学报Issue(12)：2365-2370,6.DOI:10.3969/j.issn.0372-2112.2014.12.005
基于弱监督学习的去噪受限玻尔兹曼机特征提取算法
Weakly Supervised Learning with Denoising Restricted Boltz mann Machines for Extracting Featu res
摘要
Abstract
Existing feature extraction algorithms are difficult to capture useful information from complex images .A feature extraction approach is proposed based on the weakly supervised learning with denoising restricted Boltzmann machine(RBM).First, a standard RBM is pre-trained in an unsupervised learning way,which provides a hierarchical mode with a visible layer and a hidden layer.Second,for the visible layer,a stochastic binary switch node is employed.And for the hidden layer,it is divided into fore-ground-hidden nodes and background-hidden nodes based on the score of each hidden node’s activation values and times,thus we can achieve a binary mixture denoising RBMs .Finally,the pixel-wise denoising RBMs is trained by using small number label infor-mation and stochastic switch nodes through multiplicative interaction .The experimental results show that significant performance im-provement is achieved with our proposed method .关键词
特征提取/受限玻尔兹曼机/目标识别Key words
feature extraction/restricted Boltzmann machine(RBM)/object recognition分类
信息技术与安全科学引用本文复制引用
杨杰,孙亚东,张良俊,刘海波..基于弱监督学习的去噪受限玻尔兹曼机特征提取算法[J].电子学报,2014,(12):2365-2370,6.基金项目
国家自然科学基金（No．51479159）；交通运输部软科学项目 （）
