Higher Order Recurrent Neural Networks

TL;DR

This paper introduces higher order RNNs (HORNNs), an advanced neural network structure designed to better capture long-term dependencies in sequential data, outperforming traditional RNNs and LSTMs in language modeling tasks.

Contribution

The paper proposes higher order RNNs that extend standard RNNs with additional memory units and feedback paths, improving long-term dependency modeling.

Findings

HORNNs achieve state-of-the-art results on PTB and text8 datasets.

HORNNs significantly outperform regular RNNs and LSTMs in language modeling.

Experimental results demonstrate the effectiveness of HORNNs in sequence modeling.

Abstract

In this paper, we study novel neural network structures to better model long term dependency in sequential data. We propose to use more memory units to keep track of more preceding states in recurrent neural networks (RNNs), which are all recurrently fed to the hidden layers as feedback through different weighted paths. By extending the popular recurrent structure in RNNs, we provide the models with better short-term memory mechanism to learn long term dependency in sequences. Analogous to digital filters in signal processing, we call these structures as higher order RNNs (HORNNs). Similar to RNNs, HORNNs can also be learned using the back-propagation through time method. HORNNs are generally applicable to a variety of sequence modelling tasks. In this work, we have examined HORNNs for the language modeling task using two popular data sets, namely the Penn Treebank (PTB) and English text8 data sets. Experimental results have shown that the proposed HORNNs yield the state-of-the-art performance on both data sets, significantly outperforming the regular RNNs as well as the popular LSTMs.