10 citations · 30 across the 11 of their papers we have counts for
12 papers
Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability
Anubhab Ghosh, Antoine Honoré, Dong Liu +2
In pursuit of explainability, we develop generative models for sequential data. The proposed models provide state-of-the-art classification results and robust performance for speec…
Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows
Anubhab Ghosh, Antoine Honoré, Dong Liu +2
We test the robustness of a maximum-likelihood (ML) based classifier where sequential data as observation is corrupted by noise. The hypothesis is that a generative model, that com…
A Game Theoretic Analysis of LQG Control under Adversarial Attack
Zuxing Li, György Dán, Dong Liu
Motivated by recent works addressing adversarial attacks on deep reinforcement learning, a deception attack on linear quadratic Gaussian control is studied in this paper. In the co…
Belief Propagation for Approximate Inference
Dong Liu, Minh Thành Vu, Zuxing Li +1
Belief propagation (BP) algorithm is a widely used message-passing method for inference in graphical models. BP on loop-free graphs converges in linear time. But for graphs with lo…
Region-based Energy Neural Network for Approximate Inference
Dong Liu, Ragnar Thobaben, Lars K. Rasmussen
Region-based free energy was originally proposed for generalized belief propagation (GBP) to improve loopy belief propagation (loopy BP). In this paper, we propose a neural network…
On Dominant Interference in Random Networks and Communication Reliability
Dong Liu, Baptiste Cavarec, Lars K. Rasmussen +1
In this paper, we study the characteristics of dominant interference power with directional reception in a random network modelled by a Poisson Point Process. Additionally, the Lap…
Hidden Markov Models for sepsis detection in preterm infants
Antoine Honore, Dong Liu, David Forsberg +4
We explore the use of traditional and contemporary hidden Markov models (HMMs) for sequential physiological data analysis and sepsis prediction in preterm infants. We investigate t…
Powering Hidden Markov Model by Neural Network based Generative Models
Dong Liu, Antoine Honoré, Saikat Chatterjee +1
Hidden Markov model (HMM) has been successfully used for sequential data modeling problems. In this work, we propose to power the modeling capacity of HMM by bringing in neural net…
Belief Propagation as Fully Factorized Approximation
Dong Liu, Nima N. Moghadam, Lars K. Rasmussen +2
Belief propagation (BP) can do exact inference in loop-free graphs, but its performance could be poor in graphs with loops, and the understanding of its solution is limited. This w…
Neural Network based Explicit Mixture Models and Expectation-maximization based Learning
Dong Liu, Minh Thành Vu, Saikat Chatterjee +1
We propose two neural network based mixture models in this article. The proposed mixture models are explicit in nature. The explicit models have analytical forms with the advantage…
SSFN -- Self Size-estimating Feed-forward Network with Low Complexity, Limited Need for Human Intervention, and Consistent Behaviour across Trials
Saikat Chatterjee, Alireza M. Javid, Mostafa Sadeghi +4
We design a self size-estimating feed-forward network (SSFN) using a joint optimization approach for estimation of number of layers, number of nodes and learning of weight matrices…
Entropy-regularized Optimal Transport Generative Models
Dong Liu, Minh Thành Vu, Saikat Chatterjee +1
We investigate the use of entropy-regularized optimal transport (EOT) cost in developing generative models to learn implicit distributions. Two generative models are proposed. One…