Filters








126,151 Hits in 2.8 sec

Predictive State Recurrent Neural Networks [article]

Carlton Downey, Ahmed Hefny, Boyue Li, Byron Boots, Geoffrey Gordon
2017 arXiv   pre-print
We present a new model, Predictive State Recurrent Neural Networks (PSRNNs), for filtering and prediction in dynamical systems.  ...  PSRNNs draw on insights from both Recurrent Neural Networks (RNNs) and Predictive State Representations (PSRs), and inherit advantages from both types of models.  ...  Predictive State Recurrent Neural Networks In this section we introduce Predictive State Recurrent Neural Networks (PSRNNs), a new RNN architecture inspired by PSRs.  ... 
arXiv:1705.09353v2 fatcat:ryjadauzzbcn5aai2yoj27hvae

Initialization matters: Orthogonal Predictive State Recurrent Neural Networks

Krzysztof Choromanski, Carlton Downey, Byron Boots
2018 International Conference on Learning Representations  
Predictive State Recurrent Neural Networks (PSRNNs) (Downey et al., 2017) are a state-of-the-art approach for modeling time-series data which combine the benefits of probabilistic filters and Recurrent  ...  Neural Networks into a single model.  ...  PREDICTIVE STATE RECURRENT NEURAL NETWORKS PSRNNs (Downey et al., 2017) are a recently developed RNN architecture which combine the ideas of predictive state (Boots et al., 2013) and RFs.  ... 
dblp:conf/iclr/ChoromanskiDB18 fatcat:yscqnuhdgvcxrcc4dg5j2qsdtq

Improving RNA secondary structure prediction via state inference with deep recurrent neural networks [article]

Devin Willmott and David Murrugarra and Qiang Ye
2020 arXiv   pre-print
Bidirectional long short-term memory (LSTM) neural networks have emerged as a powerful tool that can model global nonlinear sequence dependencies and have achieved state-of-the-art performances on many  ...  Accuracy is highly dependent on the success of our state inference method, and investigating the global features of our state predictions reveals that accuracy of both our state inference and structure  ...  DM thanks Christine Heitsch for introducing him into research on SHAPE-directed RNA structure prediction.  ... 
arXiv:1906.10819v2 fatcat:aq4e3vvowbg73fstu4qxql3wte

Recurrent-type Neural Networks for Real-time Short-term Prediction of Ship Motions in High Sea State [article]

Danny D'Agostino, Andrea Serani, Frederick Stern, Matteo Diez
2021 arXiv   pre-print
The prediction capability of recurrent-type neural networks is investigated for real-time short-term prediction (nowcasting) of ship motions in high sea state.  ...  Specifically, the performance of recurrent neural networks, long-short term memory, and gated recurrent units models are assessed and compared using a data set coming from computational fluid dynamics  ...  Specifically, recurrent neural network, long-short term memory, and gated recurrent units have been assessed and compared for real-time short-term prediction of wave elevation, ship motions, rudder angle  ... 
arXiv:2105.13102v1 fatcat:ibtwczugknbsbno4jbwlwe3pg4

Recurrent Neural Network-Based Prediction of TCP Transmission States from Passive Measurements

Desta Haileselassie Hagos, Paal E. Engelstad, Anis Yazidi, Oivind Kure
2018 2018 IEEE 17th International Symposium on Network Computing and Applications (NCA)  
Long Short-Term Memory (LSTM) neural networks are a state-of-the-art techniques when it comes to sequence learning and time series prediction models.  ...  In this paper, we have used LSTM-based Recurrent Neural Networks (RNN) for building a generic prediction model for Transmission Control Protocol (TCP) connection characteristics from passive measurements  ...  CONCLUSION AND FUTURE WORK In this paper, we have demonstrated the capability of a deep neural network architecture based on a learning LSTM recurrent predictive models to capture the pattern of a TCP  ... 
doi:10.1109/nca.2018.8548064 dblp:conf/nca/HagosEYK18 fatcat:qwnc6h3llvbbvgl3jam3ssigru

Improving RNA secondary structure prediction via state inference with deep recurrent neural networks

Devin Willmott, David Murrugarra, Qiang Ye
2020 Computational and Mathematical Biophysics  
Bidirectional long short-term memory (LSTM) neural networks have emerged as a powerful tool that can model global nonlinear sequence dependencies and have achieved state-of-the-art performances on many  ...  Accuracy is highly dependent on the success of our state inference method, and investigating the global features of our state predictions reveals that accuracy of both our state inference and structure  ...  DM thanks Christine Heitsch for introducing him into research on SHAPE-directed RNA structure prediction. The research of Qiang Ye is supported in part by NSF under DMS-1821144 and DMS-1620082.  ... 
doi:10.1515/cmb-2020-0002 fatcat:rczcquxfr5f2ppmjrr5noxyxae

Deeper Profiles and Cascaded Recurrent and Convolutional Neural Networks for state-of-the-art Protein Secondary Structure Prediction

Mirko Torrisi, Manaz Kaleel, Gianluca Pollastri
2019 Scientific Reports  
Porter 5 is composed of ensembles of cascaded Bidirectional Recurrent Neural Networks and Convolutional Neural Networks, incorporates new input encoding techniques and is trained on a large set of protein  ...  In spite of this, even the most sophisticated ab initio SS predictors are not able to reach the theoretical limit of three-state prediction accuracy (88-90%), while only a few predict more than the 3 traditional  ...  Cascaded bidirectional recurrent and convolutional neural networks.  ... 
doi:10.1038/s41598-019-48786-x pmid:31451723 pmcid:PMC6710256 fatcat:hzwkjm4yajbqhha4kpu62n77ba

State Degradation Trend Prediction Based on Double Hidden Layer Quantum Circuit Recurrent Unit Neural Network

LI Feng, XIANG Wang, CHEN Yong, TANG Baoping, WANG Jiaxu
2019 Journal of Mechanical Engineering  
unit neural network (DHL-QCRUNN).  ...  Key words:double hidden layer quantum circuit recurrent unit neural network;quantum computation;permutation entropy error; trend prediction;rotating machinery 0 前言 机械系统状态预测是设备故障诊断中必不可少 的一个环节,准确预测机械系统的状态退化趋势  ...  (Back-propagation neural network, BPNN)应用于高 速钢钻头磨损预测。此外,循环神经网络(Recurrent neural network, RNN) [6] [7] 在这类时间序列预测中也 有广泛应用。然而,上述预测方法仍存在诸多不足。  ... 
doi:10.3901/jme.2019.06.083 fatcat:4nna7tmsd5aevd4waulo3hhphq

Long-Term Predictions using Recurrent Neural Networks for State Changes in Polymerization Reactors
リカレントニューラルネットワークによる重合反応器内状態変化の長期予測

CHIAKI KURODA, SHOUJI HIKICHI, KOUHEI OGAWA
1998 Kagaku kogaku rombunshu  
Long-term predicting methods using neural networks (NN) are discussed for state changes in polymerization reactors.  ...  The temperature at the outlet of a continuous bulk polystyrene polymerization reactor is the present target of predictions using a layered neural network and some recurrent neural networks (RNN) .  ...  data) using four networks て 若 干 の 改 善 し か 見 られ な い が,予 測 誤 差 が 各 予 測 ス テ ップ で ほ とん ど変 化 せ ず,安 定 し た性 能 が 得 られ る とい う点 で 優 れ て い る. 3)H-RNNの 予 測 性 能 は 初 期 予 測 に お い て 特 に 優 れ て い る が,予 測 ス テ ッ プ を進 め  ... 
doi:10.1252/kakoronbunshu.24.334 fatcat:iyv326d7m5dgbe5pvz6w3mxncu

Online State of Charge Prediction in Next Generation Vehicle Batteries Using Deep Recurrent Neural Networks and Continuous Model Size Control

Steven Hespeler, Donovan Fuqua, College of Business, New Mexico State University, Las Cruces, NM, USA
2021 Journal of Energy and Power Technology  
Initial results demonstrate excellent predictions that outperform results from literature and other neural network algorithms.  ...  This investigation presents a data-driven Long-short Term Memory battery model for predicting State of Charge for lithium-ion batteries LiFePO4 for next-generation vehicle operations.  ...  Funding The authors thank the Graduate School and College of Business at New Mexico State University for partial funding of this research.  ... 
doi:10.21926/jept.2101003 fatcat:uge6d2tggbcnln2cnrmcp37rbq

Automated Prediction of Critical States of Turbogenerators During Thermal Expansion of a Rotor and a Stator Based on a Recurrent Neural Network

Dmitry Aleksandrovich Akimov, Sergey Aleksandrovich Pavelyev, Valery Dmitrievich Ivchenko
2018 International Journal of Engineering & Technology  
For machine learning of a neural network in software, a recurrent autoencoder is used. The technique of operation is with a time sequence of spectrograms.  ...  The technique of training a deep neural network is given in the classification of thermal influences on the level of vibration while a spectrogram receiving.  ...  For prediction, we used a time series analysis apparatus using a neural network of the recurrent autoencoder type.  ... 
doi:10.14419/ijet.v7i4.38.24316 fatcat:4m7ibhw5j5eu5bx4iztgut6wy4

RECURRENT-TYPE NEURAL NETWORKS FOR REAL-TIME SHORT-TERM PREDICTION OF SHIP MOTIONS IN HIGH SEA STATE

D D'Agostino, A Serani, F Stern, M Diez
2022 The 9th Conference on Computational Methods in Marine Engineering (Marine 2021)  
The prediction capability of recurrent-type neural networks is investigated for realtime short-term prediction (nowcasting) of ship motions in high sea state.  ...  Specifically, the performance of recurrent neural networks, long-short term memory, and gated recurrent units models are assessed and compared using a data set coming from computational fluid dynamics  ...  Specifically, recurrent neural network, longshort term memory, and gated recurrent units have been assessed and compared for real-time short-term prediction of wave elevation, ship motions, rudder angle  ... 
doi:10.2218/marine2021.6851 fatcat:dizklgryuzb7db4rpqmdph55zy

A MODEL FOR ENSURING INFORMATION SECURITY OF AN AUTOMATED PROCESS CONTROL SYSTEM BASED ON THE PREDICTIVE PROTECTION METHOD USING RECURRENT AND FULLY CONNECTED NEURAL NETWORKS
МОДЕЛЬ ОБЕСПЕЧЕНИЯ ИНФОРМАЦИОННОЙ БЕЗОПАСНОСТИ АВТОМАТИЗИРОВАННОЙ СИСТЕМЫ УПРАВЛЕНИЯ ТЕХНОЛОГИЧЕСКИМ ПРОЦЕССОМ НА ОСНОВЕ МЕТОДА ПРЕДИКТИВНОЙ ЗАЩИТЫ С ИСПОЛЬЗОВАНИЕМ РЕКУРРЕНТНОЙ И ПОЛНОСВЯЗНОЙ НЕЙРОННЫХ СЕТЕЙ

G.D. Asyaev, postgraduate student of the department of information security of the school of electrical engineering and computer science in FSAEI HE «South Ural State University (national research university)»., A.N. Sokolov, Ph.D., Associate professor, Head of the department of information security of the school of electrical engineering and computer science in FSAEI HE «South Ural State University (national research university)».
2021 Journal of the Ural Federal district Information security  
A MODEL FOR ENSURING INFORMATION SECURITY OF AN AUTOMATED PROCESS CONTROL SYSTEM BASED ON THE PREDICTIVE PROTECTION METHOD USING RECURRENT AND FULLY CONNECTED NEURAL NETWORKS The article analyzes the main  ...  В качестве такой сети выбрана рекуррентная нейронная сеть с сетью смеси распределений на выходе (Recurrent Neural Network with Mixture Density Network output, MDN-RNN).  ...  ASYAEV Grigorii Dmitrievich, postgraduate student of the department of information security of the school of electrical engineering and computer science in FSAEI HE «South Ural State University (national  ... 
doi:10.14529/secur210107 fatcat:pdmpsazlvfcizn2jex5wq7c62a

Research on maintenance spare parts requirement prediction based on LSTM recurrent neural network

Weixing Song, Jingjing Wu, Jianshe Kang, Jun Zhang
2021 Open Physics  
A method for predicting the requirement for maintenance spare parts based on the LSTM recurrent neural network is proposed, and the network structure is designed in detail, the realization of network training  ...  The performance comparison of predictive models such as BP neural network, generalized regression neural network, wavelet neural network, and squeeze-and-excitation network prove that the new method is  ...  recurrent neural network.  ... 
doi:10.1515/phys-2021-0072 fatcat:i5wnqmhqpvht3olxgp4qbknery

Nonlinear Dynamic Trend Modeling Using Feedback Neural Networks and Prediction Error Minimization

Yangdong Pan, Su W. Sung, Jay H. Lee
2000 IFAC Proceedings Volumes  
The recurrent feedback neural network structure we adopt is in the form of a state estimator for general nonlinear stochastic systems.  ...  We propose a nonlinear system identi cation method in which a recurrent feedback neural network is tted to available data through prediction error minimization.  ...  Fig. 1 . 1 Recurrent neural network representing the nonlinear state estimator Fig. 4 .Fig. 5 . 45 Creating Comparison of the model predictions with Fig. 6 . 6 Comparison of the prediction performance  ... 
doi:10.1016/s1474-6670(17)38642-1 fatcat:p6jb44wh3raf3flugp7y2hrtry
« Previous Showing results 1 — 15 out of 126,151 results