Next Article in Journal
Inapproximability of Rank, Clique, Boolean, and Maximum Induced Matching-Widths under Small Set Expansion Hypothesis
Previous Article in Journal
Intelligent Dynamic Backlash Agent: A Trading Strategy Based on the Directional Change Framework
Article Menu

Export Article

Open AccessArticle
Algorithms 2018, 11(11), 172; https://doi.org/10.3390/a11110172

Bidirectional Grid Long Short-Term Memory (BiGridLSTM): A Method to Address Context-Sensitivity and Vanishing Gradient

School of Software, Central South University, No. 22, Shaoshan South Road, Changsha 410075, China
*
Author to whom correspondence should be addressed.
Received: 10 July 2018 / Revised: 24 September 2018 / Accepted: 29 October 2018 / Published: 30 October 2018
(This article belongs to the Special Issue Deep Learning and Semantic Technologies)
Full-Text   |   PDF [1669 KB, uploaded 30 October 2018]   |  

Abstract

The Recurrent Neural Network (RNN) utilizes dynamically changing time information through time cycles, so it is very suitable for tasks with time sequence characteristics. However, with the increase of the number of layers, the vanishing gradient occurs in the RNN. The Grid Long Short-Term Memory (GridLSTM) recurrent neural network can alleviate this problem in two dimensions by taking advantage of the two dimensions calculated in time and depth. In addition, the time sequence task is related to the information of the current moment before and after. In this paper, we propose a method that takes into account context-sensitivity and gradient problems, namely the Bidirectional Grid Long Short-Term Memory (BiGridLSTM) recurrent neural network. This model not only takes advantage of the grid architecture, but it also captures information around the current moment. A large number of experiments on the dataset LibriSpeech show that BiGridLSTM is superior to other deep LSTM models and unidirectional LSTM models, and, when compared with GridLSTM, it gets about 26 percent gain improvement. View Full-Text
Keywords: LSTM; bidirectional grid LSTM; time sequence task; speech recognition LSTM; bidirectional grid LSTM; time sequence task; speech recognition
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Fei, H.; Tan, F. Bidirectional Grid Long Short-Term Memory (BiGridLSTM): A Method to Address Context-Sensitivity and Vanishing Gradient. Algorithms 2018, 11, 172.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Algorithms EISSN 1999-4893 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top