Text classification based on deep belief network and softmax regression. Jiang, M., Liang, Y., Feng, X., Fan, X., Pei, Z., Xue, Y., & Guan, R. Neural Computing and Applications, 29(1):61–70, 2018. Publisher: Springer Londondoi abstract bibtex 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.
@article{jiang_text_2018,
title = {Text classification based on deep belief network and softmax regression},
volume = {29},
issn = {09410643},
doi = {10.1007/s00521-016-2401-x},
abstract = {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.},
number = {1},
journal = {Neural Computing and Applications},
author = {Jiang, Mingyang and Liang, Yanchun and Feng, Xiaoyue and Fan, Xiaojing and Pei, Zhili and Xue, Yu and Guan, Renchu},
year = {2018},
note = {Publisher: Springer London},
keywords = {Deep belief networks, Feature learning, L-BFGS, Restricted Boltzmann machines, Softmax model},
pages = {61--70},
}
Downloads: 0
{"_id":"C55nAFGeJwdcHnmWW","bibbaseid":"jiang-liang-feng-fan-pei-xue-guan-textclassificationbasedondeepbeliefnetworkandsoftmaxregression-2018","author_short":["Jiang, M.","Liang, Y.","Feng, X.","Fan, X.","Pei, Z.","Xue, Y.","Guan, R."],"bibdata":{"bibtype":"article","type":"article","title":"Text classification based on deep belief network and softmax regression","volume":"29","issn":"09410643","doi":"10.1007/s00521-016-2401-x","abstract":"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.","number":"1","journal":"Neural Computing and Applications","author":[{"propositions":[],"lastnames":["Jiang"],"firstnames":["Mingyang"],"suffixes":[]},{"propositions":[],"lastnames":["Liang"],"firstnames":["Yanchun"],"suffixes":[]},{"propositions":[],"lastnames":["Feng"],"firstnames":["Xiaoyue"],"suffixes":[]},{"propositions":[],"lastnames":["Fan"],"firstnames":["Xiaojing"],"suffixes":[]},{"propositions":[],"lastnames":["Pei"],"firstnames":["Zhili"],"suffixes":[]},{"propositions":[],"lastnames":["Xue"],"firstnames":["Yu"],"suffixes":[]},{"propositions":[],"lastnames":["Guan"],"firstnames":["Renchu"],"suffixes":[]}],"year":"2018","note":"Publisher: Springer London","keywords":"Deep belief networks, Feature learning, L-BFGS, Restricted Boltzmann machines, Softmax model","pages":"61–70","bibtex":"@article{jiang_text_2018,\n\ttitle = {Text classification based on deep belief network and softmax regression},\n\tvolume = {29},\n\tissn = {09410643},\n\tdoi = {10.1007/s00521-016-2401-x},\n\tabstract = {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.},\n\tnumber = {1},\n\tjournal = {Neural Computing and Applications},\n\tauthor = {Jiang, Mingyang and Liang, Yanchun and Feng, Xiaoyue and Fan, Xiaojing and Pei, Zhili and Xue, Yu and Guan, Renchu},\n\tyear = {2018},\n\tnote = {Publisher: Springer London},\n\tkeywords = {Deep belief networks, Feature learning, L-BFGS, Restricted Boltzmann machines, Softmax model},\n\tpages = {61--70},\n}\n\n","author_short":["Jiang, M.","Liang, Y.","Feng, X.","Fan, X.","Pei, Z.","Xue, Y.","Guan, R."],"key":"jiang_text_2018","id":"jiang_text_2018","bibbaseid":"jiang-liang-feng-fan-pei-xue-guan-textclassificationbasedondeepbeliefnetworkandsoftmaxregression-2018","role":"author","urls":{},"keyword":["Deep belief networks","Feature learning","L-BFGS","Restricted Boltzmann machines","Softmax model"],"metadata":{"authorlinks":{}},"html":""},"bibtype":"article","biburl":"https://bibbase.org/zotero/ifromm","dataSources":["N4kJAiLiJ7kxfNsoh"],"keywords":["deep belief networks","feature learning","l-bfgs","restricted boltzmann machines","softmax model"],"search_terms":["text","classification","based","deep","belief","network","softmax","regression","jiang","liang","feng","fan","pei","xue","guan"],"title":"Text classification based on deep belief network and softmax regression","year":2018}