Filters








38,118 Hits in 3.3 sec

Sequence Modeling using Gated Recurrent Neural Networks [article]

Mohammad Pezeshki
2015 arXiv   pre-print
In this paper, we have used Recurrent Neural Networks to capture and model human motion data and generate motions by prediction of the next immediate data point at each time-step.  ...  Our RNN is armed with recently proposed Gated Recurrent Units which has shown promising results in some sequence modeling problems such as Machine Translation and Speech Synthesis.  ...  Generative Recurrent Neural Network We can use a Recurrent Neural Network as a generative model in a way that the output of the network in time-step t − 1 defines a probability distribution over the next  ... 
arXiv:1501.00299v1 fatcat:tt2w4lymovhezbcl7hdpwxgbta

Protein Secondary Structure Prediction using Recurrent Neural Networks

2020 International journal of recent technology and engineering  
This paper contrasts the different type of recurrent network in recurrent neural networks (RNNs).  ...  The core achievement of this paper is a group of recurrent neural networks (RNNs) that can manage high-level relational features from a pair of input protein sequence and target protein sequences.  ...  Gated Recurrent Neural Networks Here,the performance is evaluated using newly designed recurrent units LSTM and GRU on protein amino acid sequence dataset.  ... 
doi:10.35940/ijrte.e6137.018520 fatcat:qthd3sxfurhdzavmc42yecqgui

Fusion Recurrent Neural Network [article]

Yiwen Sun, Yulu Wang, Kun Fu, Zheng Wang, Changshui Zhang, Jieping Ye
2020 arXiv   pre-print
In this work, we propose a novel, succinct and promising RNN - Fusion Recurrent Neural Network (Fusion RNN). Fusion RNN is composed of Fusion module and Transport module every time step.  ...  model based on Fusion RNN.  ...  Can we use a recurrent neural network without gated units to achieve similar performance in sequence learning tasks?  ... 
arXiv:2006.04069v1 fatcat:hroig6ipofgoxh2mp3d5azo6f4

Multi-Language Identification Using Convolutional Recurrent Neural Network [article]

Vrishabh Ajay Lakhani, Rohan Mahadev
2017 arXiv   pre-print
To achieve this, we use the novel approach of using a Convolutional Recurrent Neural Network using Long Short Term Memory (LSTM) or a Gated Recurrent Unit (GRU) for forward propagation of the neural network  ...  Our hypothesis is that the performance of using polyphonic sound sequence as features and both LSTM and GRU as the gating mechanisms for the neural network outperform the traditional MFCC features using  ...  Traditionally, Convolutional recurrent neural network are used for scene labelling [7] , that is, using Convolutional Neural Networks with Intra-layer Recurrent Connections, we use this novel approach  ... 
arXiv:1611.04010v2 fatcat:glks4dpg75hfjjsj2ronijrkym

Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling [article]

Junyoung Chung and Caglar Gulcehre and KyungHyun Cho and Yoshua Bengio
2014 arXiv   pre-print
In this paper we compare different types of recurrent units in recurrent neural networks (RNNs).  ...  We evaluate these recurrent units on the tasks of polyphonic music modeling and speech signal modeling.  ...  Background: Recurrent Neural Network A recurrent neural network (RNN) is an extension of a conventional feedforward neural network, which is able to handle a variable-length sequence input.  ... 
arXiv:1412.3555v1 fatcat:ua6m7avqkzcmjdfmxiqybyrtkm

Deep Learning Based Recurrent Neural Networks to Enhance the Performance of Wind Energy Forecasting: A Review

Senthil Kumar Paramasivan
2021 Revue d'intelligence artificielle : Revue des Sciences et Technologies de l'Information  
The present paper focuses on the critical analysis of wind energy forecasting using deep learning based Recurrent neural networks (RNN) models.  ...  It explores RNN and its variants, such as simple RNN, Long Short Term Memory (LSTM), Gated Recurrent Unit (GRU), and Bidirectional RNN models.  ...  Gated Recurrent Unit (GRU) The extended version of RNN, which is also an alternative network model to LSTM for handling the vanishing gradient problem of the basic recurrent neural networks, is the gated  ... 
doi:10.18280/ria.350101 fatcat:kngcr6knszchnhjebmdhnurs2y

Gated Graph Convolutional Recurrent Neural Networks [article]

Luana Ruiz, Fernando Gama, Alejandro Ribeiro
2019 arXiv   pre-print
In this paper, we propose a Graph Convolutional Recurrent Neural Network (GCRNN) architecture specifically tailored to deal with these problems.  ...  GCRNNs use convolutional filter banks to keep the number of trainable parameters independent of the size of the graph and of the time sequences considered.  ...  GRAPH CONVOLUTIONAL RECURRENT NEURAL NETWORKS A recurrent neural network (RNN) approximates the temporal dependencies of a sequence {x t } using a hidden Markov model, i.e. x t+1 ≈ g(x t , h t ) for  ... 
arXiv:1903.01888v3 fatcat:d2xfoxetfbfxfexfgf4wi62qr4

Estimating Forces of Robotic Pouring Using a LSTM RNN [article]

Kyle Mott
2019 arXiv   pre-print
In machine learning, it is very important for a robot to be able to estimate dynamics from sequences of input data. This problem can be solved using a recurrent neural network.  ...  The results of this paper will be used for artificial intelligence research and identify the capabilities of a LSTM recurrent neural network architecture to estimate dynamics of a system.  ...  Gated Recurrent Unit (GRU) have been used in recurrent neural networks to deal with time sequential data and gradient problems.  ... 
arXiv:1904.09980v2 fatcat:3nlap3pqr5fqjmsb3ypvllev64

Protein Secondary Structure Prediction with Gated Recurrent Neural Networks

2019 VOLUME-8 ISSUE-10, AUGUST 2019, REGULAR ISSUE  
The deep learning method is suitable for high level relation feature from the target protein sequence. Recurrent Neural Network(RNN) handle sequence data in effective manner.  ...  Experiment conducted on a well-known standard data set of the RCSB[12] shows that our model is extensively better than the state-of-the-art methods in different statistical measurement.  ...  THE DEEP LEARNING MODEL The type of neural network designed to handle sequencing dependence is called a recurrent neural network.  ... 
doi:10.35940/ijitee.a4546.129219 fatcat:xwzll7spdfgazcqmt37hwe63na

Simplified Minimal Gated Unit Variations for Recurrent Neural Networks [article]

Joel Heck, Fathi M. Salem
2017 arXiv   pre-print
Recurrent neural networks with various types of hidden units have been used to solve a diverse range of problems involving sequence data.  ...  One model variant, namely MGU2, performed better than MGU on the datasets considered, and thus may be used as an alternate to MGU or GRU in recurrent neural networks.  ...  CONCLUSIONS We described and evaluated three variant models of the original minimal gated unit (MGU) model for use in recurrent neural networks.  ... 
arXiv:1701.03452v1 fatcat:xqcfriotrrh4par3g5r2gd5euu

Gesture Recognition with a Convolutional Long Short-Term Memory Recurrent Neural Network

Eleni Tsironi, Pablo V. A. Barros, Stefan Wermter
2016 The European Symposium on Artificial Neural Networks  
Inspired by the adequacy of convolutional neural networks in implicit extraction of visual features and the efficiency of Long Short-Term Memory Recurrent Neural Networks in dealing with long-range temporal  ...  dependencies, we propose a Convolutional Long Short-Term Memory Recurrent Neural Network (CNNLSTM) for the problem of dynamic gesture recognition.  ...  Hidden Markov Models [1] , Dynamic Time Warping [2] , Recurrent Neural Networks [3] , Echo State Networks [4] ).  ... 
dblp:conf/esann/TsironiBW16 fatcat:ttfhdzdygnblni3hlwf2slfoom

Deep Learning Approach for Human Action Recognition Using Gated Recurrent Unit Neural Networks and Motion Analysis

Neziha Jaouedi, Noureddine Boujnah, Med Salim Bouhlel
2019 Journal of Computer Science  
Here the Recurrent Neural Networks (RNN) with hidden unit has demonstrated advanced performance on tasks as varied as image captioning and handwriting recognition.  ...  Specifically Gated Recurrent Unit (GRU) is able to learn and take advantage of sequential and temporal data required for video recognition.  ...  Human Action Recognition To recognize a human action in sequence of video using Recurrent Neural Networks with Gated Recurrent Unit, we must trained model and classify action.  ... 
doi:10.3844/jcssp.2019.1040.1049 fatcat:ger477jzfjh7rm6ezh3myiq2m4

Cerebral LSTM: A Better Alternative for Single- and Multi-Stacked LSTM Cell-Based RNNs

Ravin Kumar
2020 SN Computer Science  
Obtained results showed that recurrent neural network constructed using single Cerebral LSTM cell outperformed both recurrent neural network with single LSTM cell and recurrent neural network with two-stacked  ...  LSTM is one such popular repeating cell unit used for building these recurrent neural network-based deep learning architectures.  ...  [9] used LSTM cells as a basic unit in recurrent neural network of both encoder and decoder parts of sequenceto-sequence model for performing language translation.  ... 
doi:10.1007/s42979-020-0101-1 dblp:journals/sncs/Kumar20a fatcat:srpybybsnze3biwygqlfiumusy

A Recurrent Neural Network with Non-gesture Rejection Model for Recognizing Gestures with Smartphone Sensors [chapter]

Myeong-Chun Lee, Sung-Bae Cho
2013 Lecture Notes in Computer Science  
We have modified BLSTM (Bidirectional Long Short-Term Memory) recurrent neural network with non-gesture rejection model to deal with the problem.  ...  A BLSTM model classifies the input into the gesture and non-gesture classes, and the specific BLSTM models for the gestures further classify it into one of twenty gestures. 24,850 sequence data are used  ...  LSTM is an extension of the recurrent neural network. It uses the three gates that can store and access the data collected from the rest of the network.  ... 
doi:10.1007/978-3-642-45062-4_4 fatcat:w5ponnfgcjckvocvvi45o4z2ti

Malicious URL Detection Based on Improved Multilayer Recurrent Convolutional Neural Network Model

Zuguo Chen, Yanglong Liu, Chaoyang Chen, Ming Lu, Xuzhuo Zhang, Entao Luo
2021 Security and Communication Networks  
Finally, the extracted features are used to evaluate malicious URL by the bidirectional LSTM recurrent neural network algorithm.  ...  Thus, an improved multilayer recurrent convolutional neural network model based on the YOLO algorithm is proposed to detect malicious URL in this paper.  ...  the use of downstream neural network models.  ... 
doi:10.1155/2021/9994127 fatcat:kwj2c6qoazbyxkaxgfafnbazni
« Previous Showing results 1 — 15 out of 38,118 results