Готові списки джерел за темами / Gated Recurrent Units (GRUs)

Зміст

Статті в журналах
Дисертації
Частини книг
Тези доповідей конференцій

Добірка наукової літератури з теми "Gated Recurrent Units (GRUs)"

Автор: Grafiati

Опубліковано: 28 вересня 2022

Оформте джерело за APA, MLA, Chicago, Harvard та іншими стилями

Оберіть тип джерела:

Ознайомтеся зі списками актуальних статей, книг, дисертацій, тез та інших наукових джерел на тему "Gated Recurrent Units (GRUs)".

Біля кожної праці в переліку літератури доступна кнопка «Додати до бібліографії». Скористайтеся нею – і ми автоматично оформимо бібліографічне посилання на обрану працю в потрібному вам стилі цитування: APA, MLA, «Гарвард», «Чикаго», «Ванкувер» тощо.

Також ви можете завантажити повний текст наукової публікації у форматі «.pdf» та прочитати онлайн анотацію до роботи, якщо відповідні параметри наявні в метаданих.

Статті в журналах з теми "Gated Recurrent Units (GRUs)"

Dangovski, Rumen, Li Jing, Preslav Nakov, Mićo Tatalović, and Marin Soljačić. "Rotational Unit of Memory: A Novel Representation Unit for RNNs with Scalable Applications." Transactions of the Association for Computational Linguistics 7 (November 2019): 121–38. http://dx.doi.org/10.1162/tacl_a_00258.

Повний текст джерела

Анотація:

Stacking long short-term memory (LSTM) cells or gated recurrent units (GRUs) as part of a recurrent neural network (RNN) has become a standard approach to solving a number of tasks ranging from language modeling to text summarization. Although LSTMs and GRUs were designed to model long-range dependencies more accurately than conventional RNNs, they nevertheless have problems copying or recalling information from the long distant past. Here, we derive a phase-coded representation of the memory state, Rotational Unit of Memory (RUM), that unifies the concepts of unitary learning and associative memory. We show experimentally that RNNs based on RUMs can solve basic sequential tasks such as memory copying and memory recall much better than LSTMs/GRUs. We further demonstrate that by replacing LSTM/GRU with RUM units we can apply neural networks to real-world problems such as language modeling and text summarization, yielding results comparable to the state of the art.

Стилі APA, Harvard, Vancouver, ISO та ін.

Khadka, Shauharda, Jen Jen Chung, and Kagan Tumer. "Neuroevolution of a Modular Memory-Augmented Neural Network for Deep Memory Problems." Evolutionary Computation 27, no. 4 (December 2019): 639–64. http://dx.doi.org/10.1162/evco_a_00239.

Повний текст джерела

Анотація:

We present Modular Memory Units (MMUs), a new class of memory-augmented neural network. MMU builds on the gated neural architecture of Gated Recurrent Units (GRUs) and Long Short Term Memory (LSTMs), to incorporate an external memory block, similar to a Neural Turing Machine (NTM). MMU interacts with the memory block using independent read and write gates that serve to decouple the memory from the central feedforward operation. This allows for regimented memory access and update, giving our network the ability to choose when to read from memory, update it, or simply ignore it. This capacity to act in detachment allows the network to shield the memory from noise and other distractions, while simultaneously using it to effectively retain and propagate information over an extended period of time. We train MMU using both neuroevolution and gradient descent, and perform experiments on two deep memory benchmarks. Results demonstrate that MMU performs significantly faster and more accurately than traditional LSTM-based methods, and is robust to dramatic increases in the sequence depth of these memory benchmarks.

Стилі APA, Harvard, Vancouver, ISO та ін.

Akpudo, Ugochukwu Ejike, and Jang-Wook Hur. "A CEEMDAN-Assisted Deep Learning Model for the RUL Estimation of Solenoid Pumps." Electronics 10, no. 17 (August 25, 2021): 2054. http://dx.doi.org/10.3390/electronics10172054.

Повний текст джерела

Анотація:

This paper develops a data-driven remaining useful life prediction model for solenoid pumps. The model extracts high-level features using stacked autoencoders from decomposed pressure signals (using complementary ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm). These high-level features are then received by a recurrent neural network-gated recurrent units (GRUs) for the RUL estimation. The case study presented demonstrates the robustness of the proposed RUL estimation model with extensive empirical validations. Results support the validity of using the CEEMDAN for non-stationary signal decomposition and the accuracy, ease-of-use, and superiority of the proposed DL-based model for solenoid pump failure prognostics.

Стилі APA, Harvard, Vancouver, ISO та ін.

Shen, Wenjuan, and Xiaoling Li. "Facial expression recognition based on bidirectional gated recurrent units within deep residual network." International Journal of Intelligent Computing and Cybernetics 13, no. 4 (October 12, 2020): 527–43. http://dx.doi.org/10.1108/ijicc-07-2020-0088.

Повний текст джерела

Анотація:

Purposerecent years, facial expression recognition has been widely used in human machine interaction, clinical medicine and safe driving. However, there is a limitation that conventional recurrent neural networks can only learn the time-series characteristics of expressions based on one-way propagation information.Design/methodology/approachTo solve such limitation, this paper proposes a novel model based on bidirectional gated recurrent unit networks (Bi-GRUs) with two-way propagations, and the theory of identity mapping residuals is adopted to effectively prevent the problem of gradient disappearance caused by the depth of the introduced network. Since the Inception-V3 network model for spatial feature extraction has too many parameters, it is prone to overfitting during training. This paper proposes a novel facial expression recognition model to add two reduction modules to reduce parameters, so as to obtain an Inception-W network with better generalization.FindingsFinally, the proposed model is pretrained to determine the best settings and selections. Then, the pretrained model is experimented on two facial expression data sets of CK+ and Oulu- CASIA, and the recognition performance and efficiency are compared with the existing methods. The highest recognition rate is 99.6%, which shows that the method has good recognition accuracy in a certain range.Originality/valueBy using the proposed model for the applications of facial expression, the high recognition accuracy and robust recognition results with lower time consumption will help to build more sophisticated applications in real world.

Стилі APA, Harvard, Vancouver, ISO та ін.

Ding, Chen, Zhouyi Zheng, Sirui Zheng, Xuke Wang, Xiaoyan Xie, Dushi Wen, Lei Zhang, and Yanning Zhang. "Accurate Air-Quality Prediction Using Genetic-Optimized Gated-Recurrent-Unit Architecture." Information 13, no. 5 (April 26, 2022): 223. http://dx.doi.org/10.3390/info13050223.

Повний текст джерела

Анотація:

Air pollution is becoming a serious concern with the development of society and urban expansion, and predicting air quality is the most pressing problem for human beings. Recently, more and more machine-learning-based methods are being used to solve the air-quality-prediction problem, and gated recurrent units (GRUs) are a representative method because of their advantage for processing time-series data. However, in the same air-quality-prediction task, different researchers have always designed different structures of the GRU due to their different experiences. Data-adaptively designing a GRU structure has thus become a problem. In this paper, we propose an adaptive GRU to address this problem, and the adaptive GRU structures are determined by the dataset, which mainly contributes with three steps. Firstly, an encoding method for the GRU structure is proposed for representing the network structure in a fixed-length binary string; secondly, we define the reciprocal of the sum of the loss of each individual as the fitness function for the iteration computation; thirdly, the genetic algorithm is used for computing the data-adaptive GRU network structure, which can enhance the air-quality-prediction result. The experiment results from three real datasets in Xi’an show that the proposed method achieves better effectiveness in RMSE and SAMPE than the existing LSTM-, SVM-, and RNN-based methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

Повний текст джерела

Анотація:

Стилі APA, Harvard, Vancouver, ISO та ін.

ArunKumar, K. E., Dinesh V. Kalaga, Ch Mohan Sai Kumar, Masahiro Kawaji, and Timothy M. Brenza. "Forecasting of COVID-19 using deep layer Recurrent Neural Networks (RNNs) with Gated Recurrent Units (GRUs) and Long Short-Term Memory (LSTM) cells." Chaos, Solitons & Fractals 146 (May 2021): 110861. http://dx.doi.org/10.1016/j.chaos.2021.110861.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Oliveira, Pedro, Bruno Fernandes, Cesar Analide, and Paulo Novais. "Forecasting Energy Consumption of Wastewater Treatment Plants with a Transfer Learning Approach for Sustainable Cities." Electronics 10, no. 10 (May 12, 2021): 1149. http://dx.doi.org/10.3390/electronics10101149.

Повний текст джерела

Анотація:

A major challenge of today’s society is to make large urban centres more sustainable. Improving the energy efficiency of the various infrastructures that make up cities is one aspect being considered when improving their sustainability, with Wastewater Treatment Plants (WWTPs) being one of them. Consequently, this study aims to conceive, tune, and evaluate a set of candidate deep learning models with the goal being to forecast the energy consumption of a WWTP, following a recursive multi-step approach. Three distinct types of models were experimented, in particular, Long Short-Term Memory networks (LSTMs), Gated Recurrent Units (GRUs), and uni-dimensional Convolutional Neural Networks (CNNs). Uni- and multi-variate settings were evaluated, as well as different methods for handling outliers. Promising forecasting results were obtained by CNN-based models, being this difference statistically significant when compared to LSTMs and GRUs, with the best model presenting an approximate overall error of 630 kWh when on a multi-variate setting. Finally, to overcome the problem of data scarcity in WWTPs, transfer learning processes were implemented, with promising results being achieved when using a pre-trained uni-variate CNN model, with the overall error reducing to 325 kWh.

Стилі APA, Harvard, Vancouver, ISO та ін.

Fang, Weiguang, Yu Guo, Wenhe Liao, Shaohua Huang, Nengjun Yang, and Jinshan Liu. "A Parallel Gated Recurrent Units (P-GRUs) network for the shifting lateness bottleneck prediction in make-to-order production system." Computers & Industrial Engineering 140 (February 2020): 106246. http://dx.doi.org/10.1016/j.cie.2019.106246.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Fang, Qiang, and Xavier Maldague. "A Method of Defect Depth Estimation for Simulated Infrared Thermography Data with Deep Learning." Applied Sciences 10, no. 19 (September 29, 2020): 6819. http://dx.doi.org/10.3390/app10196819.

Повний текст джерела

Анотація:

Infrared thermography has already been proven to be a significant method in non-destructive evaluation since it gives information with immediacy, rapidity, and low cost. However, the thorniest issue for the wider application of IRT is quantification. In this work, we proposed a specific depth quantifying technique by employing the Gated Recurrent Units (GRUs) in composite material samples via pulsed thermography (PT). Finite Element Method (FEM) modeling provides the economic examination of the response pulsed thermography. In this work, Carbon Fiber Reinforced Polymer (CFRP) specimens embedded with flat bottom holes are stimulated by a FEM modeling (COMSOL) with precisely controlled depth and geometrics of the defects. The GRU model automatically quantified the depth of defects presented in the stimulated CFRP material. The proposed method evaluated the accuracy and performance of synthetic CFRP data from FEM for defect depth predictions.

Стилі APA, Harvard, Vancouver, ISO та ін.

Більше джерел

Дисертації з теми "Gated Recurrent Units (GRUs)"

Sarika, Pawan Kumar. "Comparing LSTM and GRU for Multiclass Sentiment Analysis of Movie Reviews." Thesis, Blekinge Tekniska Högskola, Fakulteten för datavetenskaper, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:bth-20213.

Повний текст джерела

Анотація:

Today, we are living in a data-driven world. Due to a surge in data generation, there is a need for efficient and accurate techniques to analyze data. One such kind of data which is needed to be analyzed are text reviews given for movies. Rather than classifying the reviews as positive or negative, we will classify the sentiment of the reviews on the scale of one to ten. In doing so, we will compare two recurrent neural network algorithms Long short term memory(LSTM) and Gated recurrent unit(GRU). The main objective of this study is to compare the accuracies of LSTM and GRU models. For training models, we collected data from two different sources. For filtering data, we used porter stemming and stop words. We coupled LSTM and GRU with the convolutional neural networks to increase the performance. After conducting experiments, we have observed that LSTM performed better in predicting border values. Whereas, GRU predicted every class equally. Overall GRU was able to predict multiclass text data of movie reviews slightly better than LSTM. GRU was computationally expansive when compared to LSTM.

Стилі APA, Harvard, Vancouver, ISO та ін.

Putchala, Manoj Kumar. "Deep Learning Approach for Intrusion Detection System (IDS) in the Internet of Things (IoT) Network using Gated Recurrent Neural Networks (GRU)." Wright State University / OhioLINK, 2017. http://rave.ohiolink.edu/etdc/view?acc_num=wright1503680452498351.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Javid, Gelareh. "Contribution à l’estimation de charge et à la gestion optimisée d’une batterie Lithium-ion : application au véhicule électrique." Thesis, Mulhouse, 2021. https://www.learning-center.uha.fr/.

Повний текст джерела

Анотація:

L'estimation de l'état de charge (SOC) est un point crucial pour la sécurité des performances et la durée de vie des batteries lithium-ion (Li-ion) utilisées pour alimenter les VE.Dans cette thèse, la précision de l'estimation de l'état de charge est étudiée à l'aide d'algorithmes de réseaux neuronaux récurrents profonds (DRNN). Pour ce faire, pour une cellule d’une batterie Li-ion, trois nouvelles méthodes sont proposées : une mémoire bidirectionnelle à long et court terme (BiLSTM), une mémoire robuste à long et court terme (RoLSTM) et une technique d'unités récurrentes à grille (GRU).En utilisant ces techniques, on ne dépend pas de modèles précis de la batterie et on peut éviter les méthodes mathématiques complexes, en particulier dans un bloc de batterie. En outre, ces modèles sont capables d'estimer précisément le SOC à des températures variables. En outre, contrairement au réseau de neurones récursif traditionnel dont le contenu est réécrit à chaque fois, ces réseaux peuvent décider de préserver la mémoire actuelle grâce aux passerelles proposées. Dans ce cas, il peut facilement transférer l'information sur de longs chemins pour recevoir et maintenir des dépendances à long terme.La comparaison des résultats indique que le réseau BiLSTM a de meilleures performances que les deux autres méthodes. De plus, le modèle BiLSTM peut travailler avec des séquences plus longues provenant de deux directions, le passé et le futur, sans problème de disparition du gradient. Cette caractéristique permet de sélectionner une longueur de séquence équivalente à une période de décharge dans un cycle de conduite, et d'obtenir une plus grande précision dans l'estimation. En outre, ce modèle s'est bien comporté face à une valeur initiale incorrecte du SOC.Enfin, une nouvelle méthode BiLSTM a été introduite pour estimer le SOC d'un pack de batteries dans un EV. Le logiciel IPG Carmaker a été utilisé pour collecter les données et tester le modèle en simulation. Les résultats ont montré que l'algorithme proposé peut fournir une bonne estimation du SOC sans utilisation de filtre dans le système de gestion de la batterie (BMS)
The State Of Charge (SOC) estimation is a significant issue for safe performance and the lifespan of Lithium-ion (Li-ion) batteries, which is used to power the Electric Vehicles (EVs). In this thesis, the accuracy of SOC estimation is investigated using Deep Recurrent Neural Network (DRNN) algorithms. To do this, for a one cell Li-ion battery, three new SOC estimator based on different DRNN algorithms are proposed: a Bidirectional LSTM (BiLSTM) method, Robust Long-Short Term Memory (RoLSTM) algorithm, and a Gated Recurrent Units (GRUs) technique. Using these, one is not dependent on precise battery models and can avoid complicated mathematical methods especially in a battery pack. In addition, these models are able to precisely estimate the SOC at varying temperature. Also, unlike the traditional recursive neural network where content is re-written at each time, these networks can decide on preserving the current memory through the proposed gateways. In such case, it can easily transfer the information over long paths to receive and maintain long-term dependencies. Comparing the results indicates the BiLSTM network has a better performance than the other two. Moreover, the BiLSTM model can work with longer sequences from two direction, the past and the future, without gradient vanishing problem. This feature helps to select a sequence length as much as a discharge period in one drive cycle, and to have more accuracy in the estimation. Also, this model well behaved against the incorrect initial value of SOC. Finally, a new BiLSTM method introduced to estimate the SOC of a pack of batteries in an Ev. IPG Carmaker software was used to collect data and test the model in the simulation. The results showed that the suggested algorithm can provide a good SOC estimation without using any filter in the Battery Management System (BMS)

Стилі APA, Harvard, Vancouver, ISO та ін.

Hagner, Johan. "Recurrent Neural Networks for End-to-End Speech Recognition : A comparison of gated units in an acoustic model." Thesis, Umeå universitet, Institutionen för datavetenskap, 2017. http://urn.kb.se/resolve?urn=urn:nbn:se:umu:diva-153234.

Повний текст джерела

Анотація:

End-to-end speech recognition is the problem of mapping raw audio signal all the way to text. In doing so the process is not explicitly divided into modules. e.g. [signal → phoneme, phoneme → word]. Recurrentneural networks equipped with specialised temporal based loss functions have recently demonstrated breakthrough results for the end-to-end problem.In this thesis we evaluate a number of neural network architectures for end-to-end learning. LSTM (Long Short Term Memory) is a specialised gated recurrent unit that preserves a signal within a neura lnetwork over period of time. GRU (Gated recurrent Unit) is a recently discovered refinement of LSTM with still unknown performance characteristics. It is reported that different architectures works better or worse depending on the problem at hand. We explore these characteristics for the end-to-end speech recognition problem. Specifically we evaluate various networks on the LibriSpeech corpus. All the audio is read in English by people from different parts of the world. The audio files are excerpts sourced from audio books. The LibriSpeech corpus is divided into both noisy and clean audio. The noisy audio is considered to be more challenging. This corpus is pre-segmented and thus contain ready sub sets for testing. These include both noisy and clean audio and we will evaluate the end-to-end models on both sets. The findings of our experiments shows that GRU can not perform on the same level as LSTM variants. Especially not when trained on noisy data where the GRU network stop improving after only a small part of the allotted training time.

Стилі APA, Harvard, Vancouver, ISO та ін.

Gattoni, Giacomo. "Improving the reliability of recurrent neural networks while dealing with bad data." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2021.

Знайти повний текст джерела

Анотація:

In practical applications, machine learning and deep learning models can have difficulty in achieving generalization, especially when dealing with training samples that are either noisy or limited in quantity. Standard neural networks do not guarantee the monotonicity of the input features with respect to the output, therefore they lack interpretability and predictability when it is known a priori that the input-output relationship should be monotonic. This problem can be encountered in the CPG industry, where it is not possible to ensure that a deep learning model will learn the increasing monotonic relationship between promotional mechanics and sales. To overcome this issue, it is proposed the combined usage of recurrent neural networks, a type of artificial neural networks specifically designed to deal with data structured as sequences, with lattice networks, conceived to guarantee monotonicity of the desired input features with respect to the output. The proposed architecture has proven to be more reliable when new samples are fed to the neural network, demonstrating its ability to infer the evolution of the sales depending on the promotions, even when it is trained on bad data.

Стилі APA, Harvard, Vancouver, ISO та ін.

Talevi, Luca, and Luca Talevi. "“Decodifica di intenzioni di movimento dalla corteccia parietale posteriore di macaco attraverso il paradigma Deep Learning”." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/17846/.

Повний текст джерела

Анотація:

Le Brain Computer Interfaces (BCI) invasive permettono di restituire la mobilità a pazienti che hanno perso il controllo degli arti: ciò avviene attraverso la decodifica di segnali bioelettrici prelevati da aree corticali di interesse al fine di guidare un arto prostetico. La decodifica dei segnali neurali è quindi un punto critico nelle BCI, richiedendo lo sviluppo di algoritmi performanti, affidabili e robusti. Tali requisiti sono soddisfatti in numerosi campi dalle Deep Neural Networks, algoritmi adattivi le cui performance scalano con la quantità di dati forniti, allineandosi con il crescente numero di elettrodi degli impianti. Impiegando segnali pre-registrati dalla corteccia di due macachi durante movimenti di reach-to-grasp verso 5 oggetti differenti, ho testato tre basilari esempi notevoli di DNN – una rete densa multistrato, una Convolutional Neural Network (CNN) ed una Recurrent NN (RNN) – nel compito di discriminare in maniera continua e real-time l’intenzione di movimento verso ciascun oggetto. In particolare, è stata testata la capacità di ciascun modello di decodificare una generica intenzione (single-class), la performance della migliore rete risultante nel discriminarle (multi-class) con o senza metodi di ensemble learning e la sua risposta ad un degrado del segnale in ingresso. Per agevolarne il confronto, ciascuna rete è stata costruita e sottoposta a ricerca iperparametrica seguendo criteri comuni. L’architettura CNN ha ottenuto risultati particolarmente interessanti, ottenendo F-Score superiori a 0.6 ed AUC superiori a 0.9 nel caso single-class con metà dei parametri delle altre reti e tuttavia maggior robustezza. Ha inoltre mostrato una relazione quasi-lineare con il degrado del segnale, priva di crolli prestazionali imprevedibili. Le DNN impiegate si sono rivelate performanti e robuste malgrado la semplicità, rendendo eventuali architetture progettate ad-hoc promettenti nello stabilire un nuovo stato dell’arte nel controllo neuroprotesico.

Стилі APA, Harvard, Vancouver, ISO та ін.

Tsakalos, Vasileios. "Sentiment classification using tree‐based gated recurrent units." Master's thesis, 2018. http://hdl.handle.net/10362/33869.

Повний текст джерела

Анотація:

Dissertation presented as the partial requirement for obtaining a Master's degree in Information Management, specialization in Knowledge Management and Business Intelligence
Natural Language Processing is one of the most challenging fields of Artificial Intelligence. The past 10 years, this field has witnessed a fascinating progress due to Deep Learning. Despite that, we haven’t achieved to build an architecture of models that can understand natural language as humans do. Many architectures have been proposed, each of them having its own strengths and weaknesses. In this report, we will cover the tree based architectures and in particular we will propose a different tree based architecture that is very similar to the Tree-Based LSTM, proposed by Tai(2015). In this work, we aim to make a critical comparison between the proposed architecture -Tree-Based GRU- with Tree-based LSTM for sentiment classification tasks, both binary and fine-grained.

Стилі APA, Harvard, Vancouver, ISO та ін.

Частини книг з теми "Gated Recurrent Units (GRUs)"

Salem, Fathi M. "Gated RNN: The Gated Recurrent Unit (GRU) RNN." In Recurrent Neural Networks, 85–100. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-89929-5_5.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Pawlicki, Marek, Adam Marchewka, Michał Choraś, and Rafał Kozik. "Gated Recurrent Units for Intrusion Detection." In Image Processing and Communications, 142–48. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-31254-1_18.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Nayak, Jagadish, Yatharth Kher, and Sarthak Sethi. "Image Captioning Using Gated Recurrent Units." In Algorithms for Intelligent Systems, 331–40. Singapore: Springer Singapore, 2020. http://dx.doi.org/10.1007/978-981-15-5243-4_30.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Bardhan, Sayanti, Sukhendu Das, and Shibu Jacob. "Visual Saliency Detection via Convolutional Gated Recurrent Units." In Neural Information Processing, 162–74. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-36711-4_15.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Kuta, Marcin, Mikołaj Morawiec, and Jacek Kitowski. "Sentiment Analysis with Tree-Structured Gated Recurrent Units." In Text, Speech, and Dialogue, 74–82. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-64206-2_9.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Huang, Bo, Hualong Huang, and Hongtao Lu. "Convolutional Gated Recurrent Units Fusion for Video Action Recognition." In Neural Information Processing, 114–23. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-70090-8_12.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Liu, Yong, Hongchang He, Xiaofei Wang, Yu Wang, and Runxing Chen. "Hyperspectral Image Classification Based on Bidirectional Gated Recurrent Units." In Lecture Notes in Electrical Engineering, 1505–10. Singapore: Springer Singapore, 2020. http://dx.doi.org/10.1007/978-981-13-9409-6_180.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Flores, Anibal, Hugo Tito-Chura, and Victor Yana-Mamani. "Wind Speed Time Series Imputation with a Bidirectional Gated Recurrent Unit (GRU) Model." In Lecture Notes in Networks and Systems, 445–58. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-89880-9_34.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Manavi, Mahdi, and Yunpeng Zhang. "A New Intrusion Detection System Based on Gated Recurrent Unit (GRU) and Genetic Algorithm." In Security, Privacy, and Anonymity in Computation, Communication, and Storage, 368–83. Cham: Springer International Publishing, 2019. http://dx.doi.org/10.1007/978-3-030-24907-6_28.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Musto, Luigi, Francesco Valenti, Andrea Zinelli, Fabio Pizzati, and Pietro Cerri. "Convolutional Gated Recurrent Units for Obstacle Segmentation in Bird-Eye-View." In Computer Aided Systems Theory – EUROCAST 2019, 87–94. Cham: Springer International Publishing, 2020. http://dx.doi.org/10.1007/978-3-030-45096-0_11.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Тези доповідей конференцій з теми "Gated Recurrent Units (GRUs)"

Zhang, Chengkun, and Junbin Gao. "Hype-HAN: Hyperbolic Hierarchical Attention Network for Semantic Embedding." In Twenty-Ninth International Joint Conference on Artificial Intelligence and Seventeenth Pacific Rim International Conference on Artificial Intelligence {IJCAI-PRICAI-20}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/ijcai.2020/552.

Повний текст джерела

Анотація:

Hyperbolic space is a well-defined space with constant negative curvature. Recent research demonstrates its odds of capturing complex hierarchical structures with its exceptional high capacity and continuous tree-like properties. This paper bridges hyperbolic space's superiority to the power-law structure of documents by introducing a hyperbolic neural network architecture named Hyperbolic Hierarchical Attention Network (Hype-HAN). Hype-HAN defines three levels of embeddings (word/sentence/document) and two layers of hyperbolic attention mechanism (word-to-sentence/sentence-to-document) on Riemannian geometries of the Lorentz model, Klein model and Poincaré model. Situated on the evolving embedding spaces, we utilize both conventional GRUs (Gated Recurrent Units) and hyperbolic GRUs with Möbius operations. Hype-HAN is applied to large scale datasets. The empirical experiments show the effectiveness of our method.

Стилі APA, Harvard, Vancouver, ISO та ін.

Chandrasekaran, Kavin, Luke Buquicchio, Walter Gerych, Emmanuel Agu, and Elke Rundensteiner. "Get Up!: Assessing Postural Activity & Transitions using Bi-Directional Gated Recurrent Units (Bi-GRUs) on Smartphone Motion Data." In 2019 IEEE Healthcare Innovations and Point of Care Technologies (HI-POCT). IEEE, 2019. http://dx.doi.org/10.1109/hi-poct45284.2019.8962729.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Otman, Maarouf, El Ayachi Rachid, and Biniz Mohamed. "Amazigh Part Of Speech Tagging using Gated recurrent units (GRU)." In 2021 7th International Conference on Optimization and Applications (ICOA). IEEE, 2021. http://dx.doi.org/10.1109/icoa51614.2021.9442662.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

ZHU, QINGXIN, HAO WANG, JIANXIAO MAO, SUOTING HU, ZHAOHUA GONG, and XINXIN ZHAO. "TEMPERATURE-INDUCED STRAIN PREDICTION FOR THE LONG-SPAN STEEL TRUSS ARCH RAILWAY BRIDGE USING THE GRU." In 3rd International Workshop on Structural Health Monitoring for Railway System (IWSHM-RS 2021). Destech Publications, Inc., 2021. http://dx.doi.org/10.12783/iwshm-rs2021/36019.

Повний текст джерела

Анотація:

The mapping for temperature-induced strains is a reliable approach to characterize bridge structures. However, the temperature field of bridge structures is intrinsically time-varying due to the time-dependent nature of the solar radiation and surrounding environments. In addition, long-span steel truss arch railway bridges consist of thousands of structural members. Capturing the accurate relationships between bridge temperature and temperature-induced strains is challenging. To explore an accurate mapping for temperature-induced strains in bridges, this study systematically investigates the temperature distributions and temperature effects on a long-span steel truss arch railway bridge based on field monitoring data. Accordingly, the relationships between temperature-induced strains and spatial temperature distributions are investigated using the principal component analysis (PCA) and gated recurrent unit (GRU), which are applied to calculate structural strains under ambient excitation using field temperature measurements. Particularly, the GRUs with different combinations of inputs, including temperature increments, principal components of temperature increments, and the recorded time of the temperature, are trained. The predictions from different GRUs are compared with the field monitoring data. Results show that temperature-induced strains are profoundly affected by the temperature field of the bridge. The temperature-induced strains can be predicted accurately using GRU in cooperation with field temperature measurements from multi-measurement points. Note that the recorded time of the bridge temperature can be employed to represent the characteristics of the temperature field during the prediction. The results of this study can improve the performance assessment methods for bridge structures, which can be utilized for the abnormal detection of bridge structures.

Стилі APA, Harvard, Vancouver, ISO та ін.

Li, Zhe, Peisong Wang, Hanqing Lu, and Jian Cheng. "Reading selectively via Binary Input Gated Recurrent Unit." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/705.

Повний текст джерела

Анотація:

Recurrent Neural Networks (RNNs) have shown great promise in sequence modeling tasks. Gated Recurrent Unit (GRU) is one of the most used recurrent structures, which makes a good trade-off between performance and time spent. However, its practical implementation based on soft gates only partially achieves the goal to control information flow. We can hardly explain what the network has learnt internally. Inspired by human reading, we introduce binary input gated recurrent unit (BIGRU), a GRU based model using a binary input gate instead of the reset gate in GRU. By doing so, our model can read selectively during interference. In our experiments, we show that BIGRU mainly ignores the conjunctions, adverbs and articles that do not make a big difference to the document understanding, which is meaningful for us to further understand how the network works. In addition, due to reduced interference from redundant information, our model achieves better performances than baseline GRU in all the testing tasks.

Стилі APA, Harvard, Vancouver, ISO та ін.

Song, Z., and L. Florez-Perez. "End-to-end GRU model for construction crew management." In The 29th EG-ICE International Workshop on Intelligent Computing in Engineering. EG-ICE, 2022. http://dx.doi.org/10.7146/aul.455.c210.

Повний текст джерела

Анотація:

Crew management is critical towards improving construction task productivity. Traditional methods for crew management on-site are heavily dependent on the experience of site managers. This paper proposes an end-to-end Gated Recurrent Units (GRU) based framework which provides site managers a more reliable and robust method for managing crews and improving productivity. The proposed framework predicts task productivity of all possible crew combinations, within a given size, from the pool of available workers using an advanced GRU model. The model has been trained with an existing database of masonry work and was found to outperform other machine learning models. The results of the framework suggest which crew combinations have the highest predicted productivity and can be used by superintendents and project managers to improve construction task productivity and better plan future projects.

Стилі APA, Harvard, Vancouver, ISO та ін.

Ma, HaoJie, Wenzhong Li, Xiao Zhang, Songcheng Gao, and Sanglu Lu. "AttnSense: Multi-level Attention Mechanism For Multimodal Human Activity Recognition." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/431.

Повний текст джерела

Анотація:

Sensor-based human activity recognition is a fundamental research problem in ubiquitous computing, which uses the rich sensing data from multimodal embedded sensors such as accelerometer and gyroscope to infer human activities. The existing activity recognition approaches either rely on domain knowledge or fail to address the spatial-temporal dependencies of the sensing signals. In this paper, we propose a novel attention-based multimodal neural network model called AttnSense for multimodal human activity recognition. AttnSense introduce the framework of combining attention mechanism with a convolutional neural network (CNN) and a Gated Recurrent Units (GRU) network to capture the dependencies of sensing signals in both spatial and temporal domains, which shows advantages in prioritized sensor selection and improves the comprehensibility. Extensive experiments based on three public datasets show that AttnSense achieves a competitive performance in activity recognition compared with several state-of-the-art methods.

Стилі APA, Harvard, Vancouver, ISO та ін.

Dey, Rahul, and Fathi M. Salem. "Gate-variants of Gated Recurrent Unit (GRU) neural networks." In 2017 IEEE 60th International Midwest Symposium on Circuits and Systems (MWSCAS). IEEE, 2017. http://dx.doi.org/10.1109/mwscas.2017.8053243.

Повний текст джерела

Стилі APA, Harvard, Vancouver, ISO та ін.

Sousa, Luiz Felipe, Adam Dreyton Ferreira Santos, and João Weyl Albuquerque Costa. "Imputação de dados ausentes através de redes neurais recorrentes no monitoramento de integridade estrutural." In Congresso Brasileiro de Inteligência Computacional. SBIC, 2021. http://dx.doi.org/10.21528/cbic2021-137.

Повний текст джерела

Анотація:

Um problema comum em grandes conjuntos de dados é a informação ausente, seja por falha nos sensores de captura, perda no transporte, ou outra situação que culmine com a perda de dados. Diante desta situação, é frequente que a decisão do pesquisador seja desconsiderar os dados ausentes, removê-los do conjunto, no entanto, essa exclusão pode gerar inferências que não são válidas, principalmente se os dados que permanecem na análise são diferentes daqueles que foram excluídos. Para lidar com este problema em conjuntos de dados de monitoramento de integridade estrutural (Structural health monitoring – SHM), este trabalho faz uso de redes neurais recorrentes Gated Recurrent Units (GRU) e Long Short-Term Memory (LSTM), para realizar a tarefa de imputação de dados ausentes. Em uma etapa anterior à imputação, foi realizada a amputação artificial dos dados, assumindo o mecanismo de dados ausentes Missing Completely at Random (MCAR), em percentuais de 25, 50 e 75%. As técnicas de imputação foram avaliadas com o uso da métrica Mean Absolute Percentage Error (MAPE). Posteriormente, foi aplicada a etapa de detecção de dano, as bases imputadas foram submetidas aos algoritmos Mahalanobis Square Distance (MSD) e Kernel Principal Component Analysis (KPCA) a fim de se obter as taxas de erros T1 e T2 detectadas. A partir dos resultados obtidos, foi possível observar que o uso da LSTM na imputação dos dados, alcançou resultados melhores que a GRU em todas as taxas de amputação, este melhor desempenho pode também ser notado na etapa de detecção de dano, onde as bases imputadas por LSTM alcançam melhores resultados de detecção de erros T1 e T2.

Стилі APA, Harvard, Vancouver, ISO та ін.

Biazon, Victor, and Reinaldo Bianchi. "Gated Recurrent Unit Networks and Discrete Wavelet Transforms Applied to Forecasting and Trading in the Stock Market." In Encontro Nacional de Inteligência Artificial e Computacional. Sociedade Brasileira de Computação - SBC, 2020. http://dx.doi.org/10.5753/eniac.2020.12167.

Повний текст джерела

Анотація:

Trading in the stock market always comes with the challenge of deciding the best action to take on each time step. The problem is intensified by the theory that it is not possible to predict stock market time series as all information related to the stock price is already contained in it. In this work we propose a novel model called Discrete Wavelet Transform Gated Recurrent Unit Network (DWT-GRU). The model learns from the data to choose between buying, holding and selling, and when to execute them. The proposed model was compared to other recurrent neural networks, with and without wavelets preprocessing, and the buy and hold strategy. The results shown that the DWT-GRU outperformed all the set baselines in the analysed stocks of the Brazilian stock market.

Стилі APA, Harvard, Vancouver, ISO та ін.

Ми пропонуємо знижки на всі преміум-плани для авторів, чиї праці увійшли до тематичних добірок літератури. Зв'яжіться з нами, щоб отримати унікальний промокод!