標題: DEEP UNFOLDING INFERENCE FOR SUPERVISED TOPIC MODEL
作者: Lee, Chao-Hsi
Chien, Jen-Tzung
電機工程學系
Department of Electrical and Computer Engineering
關鍵字: Deep unfolding;variational inference;supervised topic model
公開日期: 2016
摘要: Conventional supervised topic model for multi-class classification is inferred via the variational inference algorithm where the model parameters are estimated by maximizing the lower bound of the logarithm of marginal likelihood function over input documents and labels. The classification accuracy is constrained by the variational lower bound. In this study, we aim to improve the classification accuracy by relaxing this constraint through directly maximizing the negative cross entropy error function via a deep unfolding inference (DUI). The inference procedure for class posterior is treated as the layer-wise learning in a deep neural network. The classification accuracy in DUI is accordingly increased by using the estimated topic parameters according to the exponentiated updates. Deep learning of supervised topic model is achieved through an error back-propagation algorithm. Experimental results show the superiority of DUI to variational Bayes inference in supervised topic model.
URI: http://hdl.handle.net/11536/136361
ISBN: 978-1-4799-9988-0
ISSN: 1520-6149
期刊: 2016 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH AND SIGNAL PROCESSING PROCEEDINGS
起始頁: 2279
結束頁: 2283
Appears in Collections:Conferences Paper