A recurrent Markov state-space generative model for sequences

Anand Ramachandran, Steve Lumetta, Eric Klee, Deming Chen
Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, PMLR 89:3070-3079, 2019.

Abstract

While the Hidden Markov Model (HMM) is a versatile generative model of sequences capable of performing many exact inferences efficiently, it is not suited for capturing complex long-term structure in the data. Advanced state-space models based on Deep Neural Networks (DNN) overcome this limitation but cannot perform exact inferences. In this article, we present a new generative model for sequences that combines both aspects, the ability to perform exact inferences and the ability to model long-term structure, by augmenting the HMM with a deterministic, continuous state variable modeled through a Recurrent Neural Network. We empirically study the performance of the model on (i) synthetic data comparing it to the HMM, (ii) a supervised learning task in bioinformatics where it outperforms two DNN-based regressors and (iii) in the generative modeling of music where it outperforms many prominent DNN-based generative models.

Cite this Paper

BibTeX
@InProceedings{pmlr-v89-ramachandran19a, title = {A recurrent Markov state-space generative model for sequences}, author = {Ramachandran, Anand and Lumetta, Steve and Klee, Eric and Chen, Deming}, booktitle = {Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics}, pages = {3070--3079}, year = {2019}, editor = {Chaudhuri, Kamalika and Sugiyama, Masashi}, volume = {89}, series = {Proceedings of Machine Learning Research}, month = {16--18 Apr}, publisher = {PMLR}, pdf = {http://proceedings.mlr.press/v89/ramachandran19a/ramachandran19a.pdf}, url = {https://proceedings.mlr.press/v89/ramachandran19a.html}, abstract = {While the Hidden Markov Model (HMM) is a versatile generative model of sequences capable of performing many exact inferences efficiently, it is not suited for capturing complex long-term structure in the data. Advanced state-space models based on Deep Neural Networks (DNN) overcome this limitation but cannot perform exact inferences. In this article, we present a new generative model for sequences that combines both aspects, the ability to perform exact inferences and the ability to model long-term structure, by augmenting the HMM with a deterministic, continuous state variable modeled through a Recurrent Neural Network. We empirically study the performance of the model on (i) synthetic data comparing it to the HMM, (ii) a supervised learning task in bioinformatics where it outperforms two DNN-based regressors and (iii) in the generative modeling of music where it outperforms many prominent DNN-based generative models.} }
Endnote
%0 Conference Paper %T A recurrent Markov state-space generative model for sequences %A Anand Ramachandran %A Steve Lumetta %A Eric Klee %A Deming Chen %B Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics %C Proceedings of Machine Learning Research %D 2019 %E Kamalika Chaudhuri %E Masashi Sugiyama %F pmlr-v89-ramachandran19a %I PMLR %P 3070--3079 %U https://proceedings.mlr.press/v89/ramachandran19a.html %V 89 %X While the Hidden Markov Model (HMM) is a versatile generative model of sequences capable of performing many exact inferences efficiently, it is not suited for capturing complex long-term structure in the data. Advanced state-space models based on Deep Neural Networks (DNN) overcome this limitation but cannot perform exact inferences. In this article, we present a new generative model for sequences that combines both aspects, the ability to perform exact inferences and the ability to model long-term structure, by augmenting the HMM with a deterministic, continuous state variable modeled through a Recurrent Neural Network. We empirically study the performance of the model on (i) synthetic data comparing it to the HMM, (ii) a supervised learning task in bioinformatics where it outperforms two DNN-based regressors and (iii) in the generative modeling of music where it outperforms many prominent DNN-based generative models.
APA
Ramachandran, A., Lumetta, S., Klee, E. & Chen, D.. (2019). A recurrent Markov state-space generative model for sequences. Proceedings of the Twenty-Second International Conference on Artificial Intelligence and Statistics, in Proceedings of Machine Learning Research 89:3070-3079 Available from https://proceedings.mlr.press/v89/ramachandran19a.html.

Related Material