河北工业科技2017，Vol.34Issue(6)：421-427,7.DOI:10.7535/hbgykj.2017yx06006
基于变分自动编码器的动态主题模型
Dynamic topic model based on variational autoencoder
摘要
Abstract
The posterior distribution of traditional dynamic topic model requires complex reasoning process,and a small change in model assume will require re-deduction,meanwhile with high time cost,which restricts the variability and generality of the model.A dynamic topic model based on variational autoencoder fusing with dynamic factor graph for inference is proposed in order to improve the performance of dynamic topic model.The model makes a reparameterization trick to evidence lower bound to generate a lower estimator,and converts the hidden parameters to a group of auxiliary parameters,which makes new param-eters not depend on variational parameters;standard stochastic gradient descent method can be available to variational obj ective function directly.At the same time,integrating the dynamic factor graph on modeling the state space model weakens the proba-bilistic of the model,simplifies the optimization process,and makes effective inference.The experimental results show that this model guarantees the accuracy,and the simplified model reduces the time cost effectively,which will provide more possibilities for dynamic topic model to be applied to complex time scenarios effectively.关键词
计算机神经网络/动态主题模型/变分自动编码器/动态因子图/参数Key words
neural network/dynamic topic model/variational autoencoder/dynamic factor graph/parameter分类
信息技术与安全科学引用本文复制引用
孙凌,韩立新,勾智楠..基于变分自动编码器的动态主题模型[J].河北工业科技,2017,34(6):421-427,7.基金项目
江苏省研究生科研与实践创新计划项目(KYCX17_0486) （KYCX17_0486）
中央高校基本科研业务费专项资金(2017B708X14) （2017B708X14）
福建省信息处理与智能控制重点实验室(闽江学院)开放课题(MJUKF201740) （闽江学院）
