Author name cluster

Baiyang Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

2 papers

1 author row

AAAI Conference 2017 Conference Paper

Regularization for Unsupervised Deep Neural Nets

Baiyang Wang
Diego Klabjan

Unsupervised neural networks, such as restricted Boltzmann machines (RBMs) and deep belief networks (DBNs), are powerful tools for feature selection and pattern recognition tasks. We demonstrate that overﬁtting occurs in such models just as in deep feedforward neural networks, and discuss possible regularization methods to reduce overﬁtting. We also propose a “partial” approach to improve the efﬁciency of Dropout/DropConnect in this scenario, and discuss the theoretical justiﬁcation of these methods from model convergence and likelihood bounds. Finally, we compare the performance of these methods based on their likelihood and classiﬁcation error rates for various pattern recognition data sets.

PDF Details

AAAI Conference 2016 Conference Paper

Temporal Topic Analysis with Endogenous and Exogenous Processes

Baiyang Wang
Diego Klabjan

We consider the problem of modeling temporal textual data taking endogenous and exogenous processes into account. Such text documents arise in real world applications, including job advertisements and economic news articles, which are inﬂuenced by the ﬂuctuations of the general economy. We propose a hierarchical Bayesian topic model which imposes a ”groupcorrelated” hierarchical structure on the evolution of topics over time incorporating both processes, and show that this model can be estimated from Markov chain Monte Carlo sampling methods. We further demonstrate that this model captures the intrinsic relationships between the topic distribution and the time-dependent factors, and compare its performance with latent Dirichlet allocation (LDA) and two other related models. The model is applied to two collections of documents to illustrate its empirical performance: online job advertisements from DirectEmployers Association and journalists’ postings on BusinessInsider. com.

PDF Details