Filters








16,468 Hits in 5.8 sec

Page 370 of Neural Computation Vol. 8, Issue 2 [page]

1996 Neural Computation  
ICRA is implemented by a recurrent, hierar- chical, modular neural network that consists of a decision module and a bank of predictive modules.  ...  ., it detects the time series source that best predicts the observed data.  ... 

Review of the applications of neural networks in chemical process control — simulation and online implementation

Mohamed Azlan Hussain
1999 Artificial Intelligence in Engineering  
It also shows the multilayered neural network as the most popular network for such process control applications and also shows the lack of actual successful online applications at the present time. q  ...  This paper intend to provide an extensive review of the various applications utilizing neural networks for chemical process control, both in simulation and online implementation.  ...  [74] developed a neural-network model of a laboratory process i.e. two non-interacting tanks in series, and incorporated it in a predictive control strategy, where the network was used to predict future  ... 
doi:10.1016/s0954-1810(98)00011-9 fatcat:3l2exdspx5d2ngy6qgxse4gnry

ONE-NAS: An Online NeuroEvolution based Neural Architecture Search for Time Series Forecasting [article]

Zimeng Lyu, Travis Desell
2022 arXiv   pre-print
designing and training new recurrent neural networks (RNNs) in an online setting.  ...  Time series forecasting (TSF) is one of the most important tasks in data science, as accurate time series (TS) predictions can drive and advance a wide variety of domains including finance, transportation  ...  Therefore, we propose a novel online NeuroEvolution (NE) Neural Architecture Search (NAS) method that evolves Recurrent Neural Networks (RNNs) for time series data prediction (ONE-NAS).  ... 
arXiv:2202.13471v1 fatcat:bxzjzmsxdvcuvb6xsb4rg7meqy

A Survey of Machine Learning Techniques For Human Activity Recognition and Their Methods and Algorithm

R. Bagavathi Lakshmi
2018 International Journal of Applied Science and Engineering  
The main objective of activity recognition is to offer information on a user's actions for permitting the computing systems to proactively help users with their tasks.  ...  Convolutional Neural Networks were developed to mine local features with simple statistical features to conserve data about global form of time series.  ...  Term Memory (LSTM) Recurrent Neural Network.  ... 
doi:10.30954/2322-0465.2.2018.2 fatcat:msxxlle34zb7xf6iwdcgsrq5qm

Monitoring Time Series With Missing Values: a Deep Probabilistic Approach [article]

Oshri Barazani, David Tolpin
2022 arXiv   pre-print
Advances in time series forecasting due to adoption of multilayer recurrent neural network architectures make it possible to forecast in high-dimensional time series, and identify and classify novelties  ...  However, mainstream approaches to multi-variate time series predictions do not handle well cases when the ongoing forecast must include uncertainty, nor they are robust to missing data.  ...  There is a range of neural recurrent models of varying complexity to deal with time series forecasting.  ... 
arXiv:2203.04916v1 fatcat:zaxfuvofwvb7tdjpcq5fwpkdre

ONE-NAS

Zimeng Lyu, Travis Desell
2022 Proceedings of the Genetic and Evolutionary Computation Conference Companion  
designing and training new recurrent neural networks (RNNs) in an online setting.  ...  Time series forecasting (TSF) is one of the most important tasks in data science, as accurate time series (TS) predictions can drive and advance a wide variety of domains including finance, transportation  ...  This work presents a novel online NeuroEvolution (NE) Neural Architecture Search (NAS) method that evolves Recurrent Neural Networks (RNNs) for time series data prediction (ONE-NAS).  ... 
doi:10.1145/3520304.3528962 fatcat:22gqfwu62nfv7dz6iofjycdu6q

Towards Real-World Applications of Online Learning Spiral Recurrent Neural Networks

Rudolf SOLLACHER, Huaien GAO
2009 Journal of Intelligent Learning Systems and Applications  
We present a new solution called Spiral Recurrent Neural Networks (SpiralRNN) with an online learning based on an extended Kalman filter and gradients as in Real Time Recurrent Learning.  ...  We illustrate its stability and performance using artificial and real-life time series and compare its prediction performance to other approaches.  ...  However, traditional approaches like Elman or standard recurrent neural networks (SRN) [5] , time delay neural networks (TDNN) [6] , block-diagonal recurrent neural networks (BDRNN) [7] or echo state  ... 
doi:10.4236/jilsa.2009.11001 fatcat:5foaxtjmhreg3cpmm26hf6pnaq

Online learning of windmill time series using Long Short-term Cognitive Networks [article]

Alejandro Morales-Hernández, Gonzalo Nápoles, Agnieszka Jastrzebska, Yamisleydi Salgueiro, Koen Vanhoof
2021 arXiv   pre-print
In this paper, we use Long Short-term Cognitive Networks (LSTCNs) to forecast windmill time series in online settings.  ...  However, update the model with the new information is often very expensive to perform using traditional Recurrent Neural Networks (RNNs).  ...  Section 2 revises the literature about recurrent neural networks used to forecast windmill time series.  ... 
arXiv:2107.00425v2 fatcat:ijisghwp5rhuhidbflgtoytsfq

2014 Index IEEE Transactions on Neural Networks and Learning Systems Vol. 25

2014 IEEE Transactions on Neural Networks and Learning Systems  
., +, TNNLS Nov. 2014 2099-2109 Stability of Complex-Valued Recurrent Neural Networks With Time-Delays.  ...  Liu, Y., +, TNNLS Feb. 2014 332-343 Stability of Complex-Valued Recurrent Neural Networks With Time-De- lays.  ...  The Field of Values of a Matrix and Neural Networks. Georgiou, G.M., TNNLS Sep. 2014  ... 
doi:10.1109/tnnls.2015.2396731 fatcat:ztnfcozrejhhfdwg7t2f5xlype

Nonlinear Motion Tracking by Deep Learning Architecture

Arnav Verma, Devesh Samaiya, Karunesh K. Gupta
2018 IOP Conference Series: Materials Science and Engineering  
We achieve this by first obtaining the centroid of the object and then using the centroid as the current example for a recurrent neural network trained using real-time recurrent learning.  ...  We show that for a single object, such a recurrent neural network is highly capable of approximating the nonlinearity of its path.  ...  Such a system is called a recurrent neural network, a deep learning architecture that is known to do well for time-series data, and has a documented algorithm for online training called the real-time recurrent  ... 
doi:10.1088/1757-899x/331/1/012020 fatcat:bvaqoy54nbettn3xom4xgsfe7q

EMI-RNN – Enhanced Multilayer Independently Recurrent Neural Networks for Handover Optimization in 5G Ultra Dense Networks

Dr K Madhavi
2019 International Journal of Research in Advent Technology  
Addressing this problem of handover optimization in the deployment of UDN's this paper proposes a novel framework EMI-RNN based on the recurrent neural networks to predict the handovers in advance and  ...  With the rapid developments in the wireless communication technology, ultra dense networks (UDN) are identified as the cutting edge platform of research, in order to achieve the network capacity goals  ...  DEEP LEARNING OF THE NETWORK WITH EMI-RNN. In the context of the deep learning framework, RNN (Recurrent Neural Network) plays a major role in time series prediction.  ... 
doi:10.32622/ijrat.72201988 fatcat:zvb6gzcg7vfy3plq3ydwhkw5mu

A Survey on Machine Learning Applied to Dynamic Physical Systems [article]

Sagar Verma
2020 arXiv   pre-print
[27] uses RL to predict nonlinear time series.  ...  A recurrent neural network is used for the online modeling and control of the nonlinear motor drive system with high static and Coulomb friction.  ... 
arXiv:2009.09719v2 fatcat:7vcu6wzzg5ehhb2un5cb2gafku

Anomaly Detection of Hydropower Units Based on Recurrent Neural Network

Lei Xiong, Jiajun Liu, Feng Yang, Gang Zhang, Jian Dang
2022 Frontiers in Energy Research  
In this paper, we propose a conditional quantile regression based recurrent neural network (QRNN), which models the time dependence and probability distribution between random variables.  ...  In hydropower systems, different components will produce n-dimensional heterogeneous time series with different characteristics at all times.  ...  For random model, recurrent neural network (Dasgupta and Osogami, 2017; Lai et al., 2018) is used for time series anomaly detection.  ... 
doi:10.3389/fenrg.2022.856635 fatcat:os2d5xhtezcppfwbn22p4s3dou

Modeling Long- and Short-Term Temporal Patterns with Deep Neural Networks [article]

Guokun Lai, Wei-Cheng Chang, Yiming Yang, Hanxiao Liu
2018 arXiv   pre-print
LSTNet uses the Convolution Neural Network (CNN) and the Recurrent Neural Network (RNN) to extract short-term local dependency patterns among variables and to discover long-term patterns for time series  ...  Multivariate time series forecasting is an important machine learning problem across many domains, including predictions of solar plant energy output, electricity consumption, and traffic jam situation  ...  Deep neural networks have also been studied for time series forecasting [8, 33] , i.e., the task of using observed time series in the past to predict the unknown time series in a look-ahead horizon -the  ... 
arXiv:1703.07015v3 fatcat:x2ontsmyi5gujeijohxnl6rh6y

Neural networks: Algorithms and applications

Derong Liu, Huaguang Zhang, Sanqing Hu
2008 Neurocomputing  
time series.  ...  Wang, Men, and Lu develop an online SVM model to predict air pollutant levels using time series based on the monitored air pollutant database in Hong Kong downtown area.  ... 
doi:10.1016/j.neucom.2007.09.001 fatcat:bpuxqwm74vfm3m33j4wbwetnmu
« Previous Showing results 1 — 15 out of 16,468 results