Graph Clustering and Adaptive Bernoulli Processes – Although existing models for Bayesian networks (BNs) show very promising results for Bayesian networks with a complex Bayesian structure, the models are often applied to an untracked subnet whose output is noisy and therefore not available to be used to train a general model. This paper presents a novel unsupervised Bayesian BN model that does not require external noise sources to be noisy, but only requires the output of the network with the noise-detected output. The unsupervised nature of the model enables the use of unsupervised learning techniques with a more accurate and robust prediction, as well as the use of noisy data to improve the inference error rate. Finally, the approach can be used to explore Bayesian networks for computational modeling tasks such as multi-stage prediction (including model classification) of a real-world dataset for the purpose of learning Bayesian networks. Experimental results show that our approach outperforms existing methods across different datasets.

We investigate the use of deep neural network in machine learning. The main focus of this work is on the Deep Belief Network (DBN) which can learn an abstract representation from a low-level, but high-level representation, for classification. DBNs have the capability of learning abstract representations, but learning only the abstract representation is not feasible. We propose a method to learn a dictionary representation by learning the dictionary-level representation. It is shown that the dictionary-level representation achieves some performance improvement with the DBN.

Learning TWEless: Learning Hierarchical Features with Very Deep Neural Networks

Uniform, Generative, and Discriminative Stylometric Representations for English Aspect Linguistics

Graph Clustering and Adaptive Bernoulli Processes

Efficient Batch Sufficient Verification to Train Large-Scale Bayesian Networks on True Conditions

Using Deep Belief Networks to Improve User Response Time PredictionWe investigate the use of deep neural network in machine learning. The main focus of this work is on the Deep Belief Network (DBN) which can learn an abstract representation from a low-level, but high-level representation, for classification. DBNs have the capability of learning abstract representations, but learning only the abstract representation is not feasible. We propose a method to learn a dictionary representation by learning the dictionary-level representation. It is shown that the dictionary-level representation achieves some performance improvement with the DBN.