Class-specific pre-trained sparse autoencoders for learning effective features for document classification

Sparse autoencoder is a commonly used deep learning approach for automatically learning features from unlabelled data (unsupervised feature learning). This paper proposes class-specific (supervised) pre-trained approach based on sparse autoencoder to gain low-dimensional interesting structure of fea...

Celý popis

Uloženo v:
Podrobná bibliografie
Vydáno v:2016 8th Computer Science and Electronic Engineering (CEEC) s. 36 - 41
Hlavní autoři: Abdulhussain, Maysa I., Gan, John Q.
Médium: Konferenční příspěvek
Jazyk:angličtina
Vydáno: IEEE 01.09.2016
Témata:
Big data
Computer science
deep learning
document categorization
Electronic mail
Feature extraction
feature learning
Machine learning
Sparse autoencoder
Support vector machines
Training
On-line přístup:Získat plný text
Tagy: Přidat tag
Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!
Popis
Shrnutí:Sparse autoencoder is a commonly used deep learning approach for automatically learning features from unlabelled data (unsupervised feature learning). This paper proposes class-specific (supervised) pre-trained approach based on sparse autoencoder to gain low-dimensional interesting structure of features with high performance in document classification. Experimental results have demonstrated the advantages and usefulness of the proposed method in document classification in high-dimensional feature space, in terms of the limited number of features required to achieve good classification accuracy.
DOI:10.1109/CEEC.2016.7835885