Stochastic Convolutional Recurrent Networks

Jen-Tzung Chien, Yu Min Huang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Scopus citations


Recurrent neural network (RNN) has been widely used for sequential learning which has achieved a great success in different tasks. The temporal convolutional network (TCN), a variant of one-dimensional convolutional neural network (CNN), was also developed for sequential learning in presence of sequence data. RNN and TCN typically captures long-term and short-term features in temporal or spatial domain, respectively. This paper presents a new sequential learning, called the convolutional recurrent network (CRN), which fulfills TCN as an encoder and RNN as a decoder so that the global semantics as well as the local dependencies are simultaneously characterized from sequence data. To facilitate the interpretation and robustness in neural models, we further develop the stochastic modeling for CRN based on variational inference. The merits of CNN and RNN are then incorporated in inference of latent space which sufficiently produces a generative model for sequential prediction. Experiments on language model shows the effectiveness of stochastic CRN when compared with the other sequential machines.

Original languageEnglish
Title of host publication2020 International Joint Conference on Neural Networks, IJCNN 2020 - Proceedings
PublisherInstitute of Electrical and Electronics Engineers Inc.
ISBN (Electronic)9781728169262
StatePublished - Jul 2020
Event2020 International Joint Conference on Neural Networks, IJCNN 2020 - Virtual, Glasgow, United Kingdom
Duration: 19 Jul 202024 Jul 2020

Publication series

NameProceedings of the International Joint Conference on Neural Networks


Conference2020 International Joint Conference on Neural Networks, IJCNN 2020
CountryUnited Kingdom
CityVirtual, Glasgow


  • Convolutional neural network
  • recurrent neural network
  • sequential learning
  • stochastic modeling

Fingerprint Dive into the research topics of 'Stochastic Convolutional Recurrent Networks'. Together they form a unique fingerprint.

Cite this