Hierarchical Multiscale Recurrent Neural Networks

Junyoung Chung, Sungjin Ahn, Yoshua Bengio

Abstract: Learning both hierarchical and temporal representation has been among the long- standing challenges of recurrent neural networks. Multiscale recurrent neural networks have been considered as a promising approach to resolve this issue, yet there has been a lack of empirical evidence showing that this type of models can actually capture the temporal dependencies by discovering the latent hierarchical structure of the sequence. In this paper, we propose a novel multiscale approach, called the hierarchical multiscale recurrent neural network, that can capture the latent hierarchical structure in the sequence by encoding the temporal dependencies with different timescales using a novel update mechanism. We show some evidence that the proposed model can discover underlying hierarchical structure in the sequences without using explicit boundary information. We evaluate our proposed model on character-level language modelling and handwriting sequence generation.

TL;DR: Propose a recurrent neural network architecture that can discover the underlying hierarchical structure in the temporal data.

Conflicts: umontreal.ca, iro.umontreal.ca, google.com, nyu.edu

Keywords: Natural language processing, Deep learning

Community Implementations: [ 2 code implementations](https://www.catalyzex.com/paper/arxiv:1609.01704/code)