Powering Hidden Markov Model by Neural Network based Generative Models

by   Dong Liu, et al.

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 network based generative models. The proposed model is termed as GenHMM. In the proposed GenHMM, each HMM hidden state is associated with a neural network based generative model that has tractability of exact likelihood and provides efficient likelihood computation. A generative model in GenHMM consists of mixture of generators that are realized by flow models. A learning algorithm for GenHMM is proposed in expectation-maximization framework. The convergence of the learning GenHMM is analyzed. We demonstrate the efficiency of GenHMM by classification tasks on practical sequential data.


page 1

page 2

page 3

page 4


Robust Classification using Hidden Markov Models and Mixtures of Normalizing Flows

We test the robustness of a maximum-likelihood (ML) based classifier whe...

Normalizing Flow based Hidden Markov Models for Classification of Speech Phones with Explainability

In pursuit of explainability, we develop generative models for sequentia...

Hidden Markov Models for sepsis detection in preterm infants

We explore the use of traditional and contemporary hidden Markov models ...

Learning to Adapt by Minimizing Discrepancy

We explore whether useful temporal neural generative models can be learn...

Products of Hidden Markov Models: It Takes N>1 to Tango

Products of Hidden Markov Models(PoHMMs) are an interesting class of gen...

Neural Network based Explicit Mixture Models and Expectation-maximization based Learning

We propose two neural network based mixture models in this article. The ...

Learning Scripts as Hidden Markov Models

Scripts have been proposed to model the stereotypical event sequences fo...

Code Repositories


Generative model based HMM model

view repo