期刊
NEURAL COMPUTING & APPLICATIONS
卷 29, 期 1, 页码 61-70出版社
SPRINGER LONDON LTD
DOI: 10.1007/s00521-016-2401-x
关键词
Deep belief networks; Softmax model; Restricted Boltzmann machines; L-BFGS; Feature learning
资金
- National Natural Science Foundation of China [61163034, 61373067, 61572228, 61272207, 61472158]
- 321 Talents Project of the two level of Inner Mongolia Autonomous Region
- Inner Mongolia Talent Development Fund
- Natural Science Foundation of Inner Mongolia Autonomous Region of China [2016MS0624]
- Research Program of Science and Technology at Universities of Inner Mongolia Autonomous Region [NJZY16177]
- Science and Technology Development Program of Jilin Province [20140101195JC, 20140520070JH, 20160101247JC]
In this paper, we propose a novel hybrid text classification model based on deep belief network and softmax regression. To solve the sparse high-dimensional matrix computation problem of texts data, a deep belief network is introduced. After the feature extraction with DBN, softmax regression is employed to classify the text in the learned feature space. In pre-training procedures, the deep belief network and softmax regression are first trained, respectively. Then, in the fine-tuning stage, they are transformed into a coherent whole and the system parameters are optimized with Limited-memory Broyden-Fletcher-Goldfarb-Shanno algorithm. The experimental results on Reuters-21,578 and 20-Newsgroup corpus show that the proposed model can converge at fine-tuning stage and perform significantly better than the classical algorithms, such as SVM and KNN.
作者
我是这篇论文的作者
点击您的名字以认领此论文并将其添加到您的个人资料中。
推荐
暂无数据