3,436 Hits in 10.5 sec

Comparison Between Traditional Machine Learning Models And Neural Network Models For Vietnamese Hate Speech Detection [article]

Son T. Luu, Hung P. Nguyen, Kiet Van Nguyen, Ngan Luu-Thuy Nguyen
2020 arXiv   pre-print
Hate-speech detection on social network language has become one of the main researching fields recently due to the spreading of social networks like Facebook and Twitter.  ...  Next, we compare these two models capable of predicting the right label by referencing their confusion matrices and considering the advantages and disadvantages of each model.  ...  In our experiments, we use 4 convolutional layers with 32 filters for each layer. GRU: Gate Recurrent Unit (GRU) is a kind of Recurrent Neural Network (RNN) model and is a variance of LSTM model.  ... 
arXiv:2002.00759v1 fatcat:7uk6ydvlprbalbp2o5cm3t26ja

Twitter based Data Analysis in Natural Language Processing using a Novel Catboost Recurrent Neural Framework

V. Laxmi Narasamma, M. Sreedevi
2021 International Journal of Advanced Computer Science and Applications  
So, this research develops the novel hybrid machine learning model as Catboost Recurrent Neural Framework (CRNF) with an error pruning mechanism to analyze the Twitter data based on user opinion.  ...  Initially, the twitter-based dataset is collected that tweets based on the coronavirus COVID-19 vaccine, which are pre-processed and trained to the system.  ...  Moreover, this proposed work is utilized the twitter data for predicting the next visiting location of the user.  ... 
doi:10.14569/ijacsa.2021.0120555 fatcat:abiybw6fxzhdppelc35graowgu

Understanding predictability and exploration in human mobility

Andrea Cuttone, Sune Lehmann, Marta C. González
2018 EPJ Data Science  
The predictive performance of models in literature varies quite broadly, from over 90% to under 40%.  ...  We show that it is much easier to achieve high accuracy when predicting the time-bin location than when predicting the next place.  ...  Publisher's Note Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.  ... 
doi:10.1140/epjds/s13688-017-0129-1 fatcat:afkcttb67najdawvibwyeu2jay

Multiple Angles of Arrival Estimation using Neural Networks [article]

Jianyuan Yu
2020 arXiv   pre-print
In this paper, we propose a neural network to estimate the azimuth and elevation angles, based on the correlated matrix extracted from received data.  ...  The result shows the neural network can achieve an accurate estimation under low SNR and deal with multiple signals.  ...  Besides, Neural Network has evolved from forwarding artificial neural network to Recurrent Neural Networks (RNN), Convolution Neural Network(CNN) and many other variations.  ... 
arXiv:2002.00541v1 fatcat:5ajtqws3mzc3xajgwdva2lu4my

#StayHome or #Marathon? Social Media Enhanced Pandemic Surveillance on Spatial-temporal Dynamic Graphs [article]

Yichao Zhou, Jyun-yu Jiang, Xiusi Chen, Wei Wang
2021 arXiv   pre-print
To take advantage of the social media data, we propose a novel framework, Social Media enhAnced pandemic suRveillance Technique (SMART), which is composed of two modules: (i) information extraction module  ...  to construct heterogeneous knowledge graphs based on the extracted events and relationships among them; (ii) time series prediction module to provide both short-term and long-term forecasts of the confirmed  ...  We then propose a Dynamic Graph Neural Network (DGNN) with a Bidirectional Recurrent Neural Network (Bi-RNN) to forecast pandemic trends and suggest risk factors for each location.  ... 
arXiv:2108.03670v1 fatcat:fa5ifyhn5bdzdo4igujrsxik6e

Artificial Neural Networks-Based Machine Learning for Wireless Networks: A Tutorial [article]

Mingzhe Chen, Ursula Challita, Walid Saad, Changchuan Yin, and Mérouane Debbah
2019 arXiv   pre-print
For this purpose, we present a comprehensive overview on a number of key types of neural networks that include feed-forward, recurrent, spiking, and deep neural networks.  ...  Next-generation wireless networks must support ultra-reliable, low-latency communication and intelligently manage a massive number of Internet of Things (IoT) devices in real-time, within a highly dynamic  ...  By exploiting the correlation between users' data, their social interests, and their common interests, the accuracy of predicting future events such as users' geographic locations, next visited cells,  ... 
arXiv:1710.02913v2 fatcat:kljn2evlwba4fha4lpwxjpv4yu

DNA Sequences Classification with Deep Learning: A Survey

Samia M. Abd –Alhalem, El-Sayed M. El-Rabaie, Naglaa. F. Soliman, Salah Eldin S. E. Abdulrahman, Nabil A. Ismail, Fathi E. Abd El-samie
2021 Menoufia Journal of Electronic Engineering Research  
With the advances of the big data era in bioinformatics, applying DL techniques, the DNA sequences can be classified with accurate and scalable prediction.  ...  neural networks to hyper parameter tuning, and the most recent state-of-the-art DL architectures used in DNA classification.  ...  The rule-of-thumb is to monitor the progress and use early stopping, which can stop the training at the early stage and prevent the neural network from overfitting.  ... 
doi:10.21608/mjeer.2021.146090 fatcat:vkfpn7wb3bfqtdmxer2cli3tqu

Neural Machine Translation [article]

Philipp Koehn
2017 arXiv   pre-print
Draft of textbook chapter on neural machine translation. a comprehensive treatment of the topic, ranging from introduction to neural networks, computation graphs, description of the currently dominant  ...  Validation Set Neural network training proceeds for several epochs, i.e., full iterations over the training data. When to stop?  ...  Figure 13 . 14 : 1314 Back-propagation through time: By unfolding the recurrent neural network over a fixed number of prediction steps (here: 3), we can derive update formulas based on the training objective  ... 
arXiv:1709.07809v1 fatcat:kj23sup7yfaxvllfha4v7xbugq

Short-Term Forecasting of Electricity Consumption in Palestine Using Artificial Neural Networks

Shorouq Salahat
2017 International Journal of Artificial Intelligence & Applications  
The system analyzes the collected data of electricity consumption of the previous years, then byusing the mean value for each day and the use of Multilayer Feed-Forward with Backpropagation Neural Networks  ...  The experimental results show that the model performs good results of prediction, with low Mean Square Error (MSE).  ...  In [1] they proposed a Narx neural network to predict Iran electricity consumption, logarithmical Pre-processing over the input data is used to improve the performance.  ... 
doi:10.5121/ijaia.2017.8202 fatcat:mydkxyfbenhbtejsrrt4acwezi

From Imitation to Prediction, Data Compression vs Recurrent Neural Networks for Natural Language Processing

Juan Andres Laura, Gabriel Omar Masi, Luis Argerich
2018 Inteligencia Artificial  
In addition, Data Compression is also based on prediction.  ...  In our journey, a fundamental difference between a Data Compression Algorithm and Recurrent Neural Networks has been discovered.  ...  Alex Graves for his comments on an earlier attempt to make handwriting recognition with PAQ compressor.  ... 
doi:10.4114/intartif.vol21iss61pp30-46 fatcat:rwqclrrxnfconh6yvq3jhl4k64

D2.2 Multi-Source Analytics Methodological Foundations

Suite5, SingularLogic, The Smile Of The Child, NTUA
2018 Zenodo  
This deliverable is related to the first release of the methodology, algorithms and examples for predictive analytics and analytics over the case under investigation merging data from multiple sources.  ...  based on mobile phone calls Predicting the Next Location: A Recurrent Model with Spatial and Temporal Contexts [59] 2016 • Deep Learning • Recurrent Neural Network (ST-RNN) Two real world  ...  Tree, Random Forest, Artificial Neural Networks, Naïve Bayes, SVM (with RBF kernel) • Recurrent Neural Network (LSTM) 16,568,179 data points in January 2015 (Call Data Records) Location prediction  ... 
doi:10.5281/zenodo.1477456 fatcat:zgxdgejcdjgxlgji6roswh22iq

A Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the Prediction of Timestamp Influence on Bitcoin Value

Nahla Aljojo, Areej Alshutayri, Eman Aldhahri, Seita Almandeel, Azida Zainol
2021 IEEE Access  
That is why this current study utilized a Nonlinear Autoregressive Exogenous (NARX) Neural Network Model for the prediction timestamp influence on Bitcoin value.  ...  of Bitcoin price over timestamp developed a pattern that was predicted by NARX with less That means those involved in the transaction of bitcoin at the wrong timestamp will certainly face the uncertainty  ...  A recurrent neural network model has been used along with historical bitcoin price data in [27] .  ... 
doi:10.1109/access.2021.3124629 fatcat:3hz3yy7r65avng53s5ix4pnup4

LSTMVis: A Tool for Visual Analysis of Hidden State Dynamics in Recurrent Neural Networks [article]

Hendrik Strobelt, Sebastian Gehrmann, Hanspeter Pfister, Alexander M. Rush
2017 arXiv   pre-print
In this work, we present LSTMVIS, a visual analysis tool for recurrent neural networks with a focus on understanding these hidden state dynamics.  ...  Recurrent neural networks, and in particular long short-term memory (LSTM) networks, are a remarkably effective tool for sequence modeling that learn a dense black-box hidden representation of their sequential  ...  A recurrent neural network language model being used to compute p(w t+1 |w 1 , . . . , w t ).  ... 
arXiv:1606.07461v2 fatcat:qaotfljo6fdmxlfn6pb26yynue

Leveraging Smooth Attention Prior for Multi-Agent Trajectory Prediction [article]

Zhangjie Cao, Erdem Bıyık, Guy Rosman, Dorsa Sadigh
2022 arXiv   pre-print
, and show its advantages in terms of prediction accuracy by comparing it with the state-of-the-art approaches on both synthetic and naturalistic driving data.  ...  In this paper, we formulate an attention model for multi-agent interactions based on a total variation temporal smoothness prior and propose a trajectory prediction architecture that leverages the knowledge  ...  We then perform trajectory prediction for each agent by a recurrent neural network with the history of states and the predicted attention as input.  ... 
arXiv:2203.04421v2 fatcat:scvzx3h4bndbjbj5j6oedrdw7a

Explainable Artificial Intelligence (xAI) Approaches and Deep Meta-Learning Models [chapter]

Evren Dağlarli
2020 Advances and Applications in Deep Learning  
These artificial neural network-based models are black box models that generalize the data transmitted to it and learn from the data.  ...  This is an important open point in artificial neural networks and deep learning models.  ...  These artificial neural network-based models are black box models that generalize the data transmitted to it and learn from the data.  ... 
doi:10.5772/intechopen.92172 fatcat:sgmxtwloa5bbzb5sp7tpi75i3y
« Previous Showing results 1 — 15 out of 3,436 results