A Review of Recurrent Neural Networks: LSTM Cells and Network Architectures

2019 ◽  
Vol 31 (7) ◽  
pp. 1235-1270 ◽  
Author(s):  
Yong Yu ◽  
Xiaosheng Si ◽  
Changhua Hu ◽  
Jianxun Zhang
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Cell Structure ◽  
Relevant Information ◽  
Future Research ◽  
Sequential Data ◽  
Learning Capacity ◽  
Research Areas ◽  
Almost All

Recurrent neural networks (RNNs) have been widely adopted in research areas concerned with sequential data, such as text, audio, and video. However, RNNs consisting of sigma cells or tanh cells are unable to learn the relevant information of input data when the input gap is large. By introducing gate functions into the cell structure, the long short-term memory (LSTM) could handle the problem of long-term dependencies well. Since its introduction, almost all the exciting results based on RNNs have been achieved by the LSTM. The LSTM has become the focus of deep learning. We review the LSTM cell and its variants to explore the learning capacity of the LSTM cell. Furthermore, the LSTM networks are divided into two broad categories: LSTM-dominated networks and integrated LSTM networks. In addition, their various applications are discussed. Finally, future research directions are presented for LSTM networks.

scholarly journals Compressing Recurrent Neural Networks with Tensor Ring for Action Recognition

2019 ◽  
Vol 33 ◽  
pp. 4683-4690 ◽  
Author(s):  
Yu Pan ◽  
Jing Xu ◽  
Maolin Wang ◽  
Jinmian Ye ◽  
Fei Wang ◽  
...  
Keyword(s):  
Neural Networks ◽  
Action Recognition ◽  
Recurrent Neural Networks ◽  
Input Data ◽  
Short Term Memory ◽  
Computational Cost ◽  
Tensor Decomposition ◽  
Decomposition Methods ◽  
Low Rank ◽  
Sequential Data

Recurrent Neural Networks (RNNs) and their variants, such as Long-Short Term Memory (LSTM) networks, and Gated Recurrent Unit (GRU) networks, have achieved promising performance in sequential data modeling. The hidden layers in RNNs can be regarded as the memory units, which are helpful in storing information in sequential contexts. However, when dealing with high dimensional input data, such as video and text, the input-to-hidden linear transformation in RNNs brings high memory usage and huge computational cost. This makes the training of RNNs very difficult. To address this challenge, we propose a novel compact LSTM model, named as TR-LSTM, by utilizing the low-rank tensor ring decomposition (TRD) to reformulate the input-to-hidden transformation. Compared with other tensor decomposition methods, TR-LSTM is more stable. In addition, TR-LSTM can complete an end-to-end training and also provide a fundamental building block for RNNs in handling large input data. Experiments on real-world action recognition datasets have demonstrated the promising performance of the proposed TR-LSTM compared with the tensor-train LSTM and other state-of-the-art competitors.

Applications of Recurrent Neural Networks in Environmental Factor Forecasting: A Review

2018 ◽  
Vol 30 (11) ◽  
pp. 2855-2881 ◽  
Author(s):  
Yingyi Chen ◽  
Qianqian Cheng ◽  
Yanjun Cheng ◽  
Hao Yang ◽  
Huihui Yu
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Environmental Factor ◽  
Recurrent Neural Networks ◽  
Feedforward Neural Networks ◽  
Time Series Forecasting ◽  
Learning Ability ◽  
Future Research ◽  
Sequential Data ◽  
Novel Applications

Analysis and forecasting of sequential data, key problems in various domains of engineering and science, have attracted the attention of many researchers from different communities. When predicting the future probability of events using time series, recurrent neural networks (RNNs) are an effective tool that have the learning ability of feedforward neural networks and expand their expression ability using dynamic equations. Moreover, RNNs are able to model several computational structures. Researchers have developed various RNNs with different architectures and topologies. To summarize the work of RNNs in forecasting and provide guidelines for modeling and novel applications in future studies, this review focuses on applications of RNNs for time series forecasting in environmental factor forecasting. We present the structure, processing flow, and advantages of RNNs and analyze the applications of various RNNs in time series forecasting. In addition, we discuss limitations and challenges of applications based on RNNs and future research directions. Finally, we summarize applications of RNNs in forecasting.

scholarly journals Music emotion recognition using recurrent neural networks and pretrained models

2021 ◽  
Author(s):  
Jacek Grekow
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Recurrent Network ◽  
Sequential Data ◽  
Circumplex Model ◽  
Learning Networks ◽  
Audio Features ◽  
Svm Algorithm ◽  
Audio Feature Extraction

AbstractThe article presents conducted experiments using recurrent neural networks for emotion detection in musical segments. Trained regression models were used to predict the continuous values of emotions on the axes of Russell’s circumplex model. A process of audio feature extraction and creating sequential data for learning networks with long short-term memory (LSTM) units is presented. Models were implemented using the WekaDeeplearning4j package and a number of experiments were carried out with data with different sets of features and varying segmentation. The usefulness of dividing the data into sequences as well as the point of using recurrent networks to recognize emotions in music, the results of which have even exceeded the SVM algorithm for regression, were demonstrated. The author analyzed the effect of the network structure and the set of used features on the results of the regressors recognizing values on two axes of the emotion model: arousal and valence. Finally, the use of a pretrained model for processing audio features and training a recurrent network with new sequences of features is presented.

scholarly journals Towards Enhanced Anomaly Object Detection and Face Recognition (EAODFR) in Surveillance Videos using Recurrent Neural Networks

2019 ◽  
Vol 8 (4) ◽  
pp. 3597-3603
Keyword(s):  
Neural Networks ◽  
Face Recognition ◽  
Object Detection ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Region Of Interest ◽  
Surveillance Videos ◽  
Research Areas ◽  
Present Decade ◽  
Interest Detection

In the present decade, anomaly object detection and face recognition from surveillance videos from diverse environments have become interesting and challenging research areas in computer vision. This paper works on developing an Enhanced Anomaly Object Detection and Face Recognition (EAODFR) model using Recurrent Neural Networks (RNN). Moreover, fractional derivative based background separation has been incorporated for framing efficient background subtraction model and foreground segmentation with appropriate pixel definitions on each frame of the surveillance videos. The Region of Interest detection has been done using optimal thresholding and for detecting anomaly objects. Further, efficient face recognition has been accomplished by designing the Recurrent Neural Networks (RNN), which is implemented with Long Short-Term Memory (LSTM). The recurrent NN are trained in terms of determining anomalous objects using the extracted features in the each frame of the video. The obtained results are analyzed in terms of precision, recall and f-measure and compared with some existing face recognition models. The comparative analysis provides better results and outperforms others.

Fake News Detection Using Recurrent Neural Networks and Distributed Representations for the Portuguese Language

2021 ◽  
Author(s):  
Guilherme Zanini Moreira ◽  
Marcelo Romero ◽  
Manassés Ribeiro
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Classification Performance ◽  
Fake News ◽  
Distributed Representations ◽  
Memory Network ◽  
Long Short Term Memory ◽  
Media Channels ◽  
Damage Rule

After the advent of Web, the number of people who abandoned traditional media channels and started receiving news only through social media has increased. However, this caused an increase of the spread of fake news due to the ease of sharing information. The consequences are various, with one of the main ones being the possible attempts to manipulate public opinion for elections or promotion of movements that can damage rule of law or the institutions that represent it. The objective of this work is to perform fake news detection using Distributed Representations and Recurrent Neural Networks (RNNs). Although fake news detection using RNNs has been already explored in the literature, there is little research on the processing of texts in Portuguese language, which is the focus of this work. For this purpose, distributed representations from texts are generated with three different algorithms (fastText, GloVe and word2vec) and used as input features for a Long Short-term Memory Network (LSTM). The approach is evaluated using a publicly available labelled news dataset. The proposed approach shows promising results for all the three distributed representation methods for feature extraction, with the combination word2vec+LSTM providing the best results. The results of the proposed approach shows a better classification performance when compared to simple architectures, while similar results are obtained when the approach is compared to deeper architectures or more complex methods.

Sign in / Sign up

Export Citation Format

Share Document