Готові списки джерел за темами / Recurrent Elman neural network

Зміст

  1. Статті в журналах
  2. Дисертації
  3. Книги
  4. Частини книг
  5. Тези доповідей конференцій
  6. Звіти організацій

Добірка наукової літератури з теми "Recurrent Elman neural network"

Автор: Grafiati
Опубліковано: 30 травня 2022
Оновлено: 31 травня 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 "Recurrent Elman neural network".

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 "Recurrent Elman neural network"

1

Wutsqa, Dhoriva Urwatul, and Anisa Nurjanah. "Breast Cancer Classification Using Fuzzy Elman Recurrent Neural Network." Journal of Advanced Research in Dynamical and Control Systems 11, no. 11-SPECIAL ISSUE (November 20, 2019): 946–53. http://dx.doi.org/10.5373/jardcs/v11sp11/20193119.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Mohana Sundaram, N., and S. N. Sivanandam. "A hybrid elman neural network predictor for time series prediction." International Journal of Engineering & Technology 7, no. 2.20 (April 18, 2018): 159. http://dx.doi.org/10.14419/ijet.v7i2.20.12799.

Повний текст джерела
Анотація:
Artificial Neural Networks have become popular in the world of prediction and forecasting due to their nonlinear nonparametric adaptive-learning property. They become an important tool in data analysis and data mining applications. Elman neural network due to its recurrent nature and dynamic processing capabilities can perform the prediction process with a good range of accuracy. In this paper an Elman recurrent Neural Network is hybridised with a time delay called a tap delay line for time series prediction process to improve its performance. The Elman neural network with the time delay inputs is trained tested and validated using the solar sun spot time series data that contains the monthly mean sunspot numbers for a 240 year period having 2899 data values. The results confirm that the proposed Elman network hybridised with time delay inputs can predict the time series with more accurately and effectively than the existing methods.
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Aribowo, Widi. "ELMAN-RECURRENT NEURAL NETWORK FOR LOAD SHEDDING OPTIMIZATION." SINERGI 24, no. 1 (January 14, 2020): 29. http://dx.doi.org/10.22441/sinergi.2020.1.005.

Повний текст джерела
Анотація:
Load shedding plays a key part in the avoidance of the power system outage. The frequency and voltage fluidity leads to the spread of a power system into sub-systems and leads to the outage as well as the severe breakdown of the system utility. In recent years, Neural networks have been very victorious in several signal processing and control applications. Recurrent Neural networks are capable of handling complex and non-linear problems. This paper provides an algorithm for load shedding using ELMAN Recurrent Neural Networks (RNN). Elman has proposed a partially RNN, where the feedforward connections are modifiable and the recurrent connections are fixed. The research is implemented in MATLAB and the performance is tested with a 6 bus system. The results are compared with the Genetic Algorithm (GA), Combining Genetic Algorithm with Feed Forward Neural Network (hybrid) and RNN. The proposed method is capable of assigning load releases needed and more efficient than other methods.
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Jiwa Permana, Agus Aan, and Widodo Prijodiprodjo. "Sistem Evaluasi Kelayakan Mahasiswa MagangMenggunakan Elman Recurrent Neural Network." IJCCS (Indonesian Journal of Computing and Cybernetics Systems) 8, no. 1 (January 31, 2014): 37. http://dx.doi.org/10.22146/ijccs.3494.

Повний текст джерела
Анотація:
AbstrakJaringan Syaraf Tiruan (JST) dapat digunakan untuk memecahkan permasalahan tertentu seperti prediksi, klasifikasi, pengolahan data, dan robotik.Berdasarkan paparan tersebut, sehingga dalam penelitian ini mencoba menerapkan JST untuk menangani permasalahan dalam program magang yang sedang dihadapi dalam upaya untuk meningkatkan kompetensi, pengalaman, serta melatih softskill mahasiswa.Sistem yang dikembangkan dapat digunakan untuk mengevaluasi kelayakan mahasiswa dalam program magang ke luar daerah dengan menerapkan Elman Recurrent Neural Network (ERNN), sehingga dapat memberikan informasi yang akurat kepada pihak jurusan untuk menentukan keputusan yang tepat.Struktur Elman dipilih karena dapat membuat iterasi jauh lebih cepat sehingga memudahkan proses konvergensi. Adapun metode pembelajaran yang digunakan adalah Backpropagation ThroughTime dengan model epochwise training mode. Sistem diimplementasikan dengan menggunakan bahasa pemrograman C# dengan basis data MySQL. Vektor input yang digunakan terdiri dari 11 variabel. Hasil penelitian menunjukkan bahwa sistem yang dikembangkan akan cepat mengalami konvergen dan mampu mencapai nilai error paling optimal (minimum error) apabila menggunakan 1 hidden layer dengan jumlah neuron 20 unit. Akurasi terbaik dapat diperoleh dengan menggunakan LR sebesar 0.01 dan momentum 0.85 dimana akurasi rata-rata dalam pengujian mencapai 87.50%. Kata kunci—Evaluasi, Kelayakan, Jaringan Syaraf Tiruan (JST), Elman Recurrent Neural Network, Magang Abstract Artificial Neural Network (ANN) can be used to solve specific problems such as prediction, classification, data processing, and robotics. Based on the exposure, so in this study tried to apply neural networks to handle problems in apprentice program facing in an effort to increase the competence, experience and soft skills training students. The system developed can be used to evaluate the students in the apprentice program to other regions by applying the Elman Recurrent Neural Network (ERNN), so it can provide accurate information to the department to determine appropriate decisions. Elman structure was chosen because it can be create much more rapidly iterations so as to facilitate the convergence process. The learning method used is Backpropagation Through Time with model epochwise training mode. The system is implemented using the C # programming language with a MySQL database. Input vector used consists of 11 variables. The results showed that the developed system will rapidly converge and can reach optimal error value (minimum error) when using one hidden layer with 20 units number of neurons. Best accuracy can be obtained using the LR of 0.01 and momentum 0.85 which average accuracy reaches 87.50% in testing. Keywords—Evaluation, Feasibility, Artificial Neural Network (ANN), Elman Recurrent Neural Network, Apprenticeship
Стилі APA, Harvard, Vancouver, ISO та ін.
5

You, Wen Xia, Jun Xiao Chang, Zi Heng Zhou, and Ji Lu. "Short-Term Load Forecasting Based on GA-Elman Model." Advanced Materials Research 986-987 (July 2014): 520–23. http://dx.doi.org/10.4028/www.scientific.net/amr.986-987.520.

Повний текст джерела
Анотація:
Elman Neural Network is a typical neural-network which shares the characteristics of multiple-layer and dynamic recurrent, and it’s more suitable than BP Neural Network when it’s applied to forecast the short-term load with periodicity and similarity. To solve the problem that Elman Neural Network lacks learning efficiency, GA-Elman model is established by optimizing the weights and thresholds using Genetic Algorithm. An example is then given to prove the effectiveness of GA-Elman model, using the load data of a certain region. Relative error and MSE have been considered as criterions to analyze the results of load forecasting. By comparing the results calculated by BP, Elman and GA-Elman model, the effectiveness of GA-Elman model is verified, which will improve the accuracy of short-term load forecasting.
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Wang, Jie, Jun Wang, Wen Fang, and Hongli Niu. "Financial Time Series Prediction Using Elman Recurrent Random Neural Networks." Computational Intelligence and Neuroscience 2016 (2016): 1–14. http://dx.doi.org/10.1155/2016/4742515.

Повний текст джерела
Анотація:
In recent years, financial market dynamics forecasting has been a focus of economic research. To predict the price indices of stock markets, we developed an architecture which combined Elman recurrent neural networks with stochastic time effective function. By analyzing the proposed model with the linear regression, complexity invariant distance (CID), and multiscale CID (MCID) analysis methods and taking the model compared with different models such as the backpropagation neural network (BPNN), the stochastic time effective neural network (STNN), and the Elman recurrent neural network (ERNN), the empirical results show that the proposed neural network displays the best performance among these neural networks in financial time series forecasting. Further, the empirical research is performed in testing the predictive effects of SSE, TWSE, KOSPI, and Nikkei225 with the established model, and the corresponding statistical comparisons of the above market indices are also exhibited. The experimental results show that this approach gives good performance in predicting the values from the stock market indices.
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Radjabaycolle, Jefri, and Reza Pulungan. "PREDIKSI PENGGUNAAN BANDWIDTH MENGGUNAKAN ELMAN RECURRENT NEURAL NETWORK." BAREKENG: Jurnal Ilmu Matematika dan Terapan 10, no. 2 (December 1, 2016): 127–35. http://dx.doi.org/10.30598/barekengvol10iss2pp127-135.

Повний текст джерела
Анотація:
Jaringan Syaraf Tiruan (JST) sering dipakai dalam menyelesaikan permasalahan tertentu seperti prediksi, klasifikasi, dan pengolahan data. Berdasarkan hal tersebut, dalam penelitian ini mencoba menerapkan JST untuk menangani permasalahan dalam prediksi penggunaan bandwidth. Sistem yang dikembangkan dapat digunakan untuk memprediksi pengunaan bandwidth dengan menerapkan Elman Recurrent Neural Network (ERNN). Struktur Elman dipilih karena dapat membuat iterasi jauh lebih cepat sehingga memudahkan proses konvergensi.. Vektor input yang digunakan menggunakan windows size. Hasil penelitian dengan menggunakan target error sebesar 0.001 menunjukkan nilai MSE terkecil yaitu pada windows size 11 dengan nilai 0.002833. Kemudian dengan menggunakan 13 neuron pada hidden layer diperoleh nilai error paling optimal (minimum error) sebesar 0.003725.
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Wang, Fang, Sai Tang, and Menggang Li. "Advantages of Combining Factorization Machine with Elman Neural Network for Volatility Forecasting of Stock Market." Complexity 2021 (May 22, 2021): 1–12. http://dx.doi.org/10.1155/2021/6641298.

Повний текст джерела
Анотація:
With a focus in the financial market, stock market dynamics forecasting has received much attention. Predicting stock market fluctuations is usually challenging due to the nonlinear and nonstationary time series of stock prices. The Elman recurrent network is renowned for its capability of dealing with dynamic information, which has made it a successful application to predicting. We developed a hybrid approach which combined Elman recurrent network with factorization machine (FM) technique, i.e., the FM-Elman neural network, to predict stock market volatility. In this paper, the Standard & Poor’s 500 Composite Stock Price (S&P 500) index, the Dow Jones industrial average (DJIA) index, the Shanghai Stock Exchange Composite (SSEC) index, and the Shenzhen Securities Component Index (SZI) were used to demonstrate the validity of our proposed FM-Elman model in time-series prediction. The results were compared with predictions obtained from the other two models which are basic BP neural network and the Elman neural network. Some experiments showed that the FM-Elman model outperforms others through different accuracy measures. Furthermore, the effects of volatility degree on prediction performance from different stock indexes were investigated. An interesting phenomenon had been found through some numerical experiments on the effects of different user-specified dimensions on the proposed FM-Elman neural network.
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Wang, Qiang. "Intelligent Identification of Flow Regime Based on a Novel Neural Network." Applied Mechanics and Materials 635-637 (September 2014): 1715–18. http://dx.doi.org/10.4028/www.scientific.net/amm.635-637.1715.

Повний текст джерела
Анотація:
A noveol neural network of Elman is typically dynamic recurrent neural network. A novel method of flow regime identification based on Elman neural network and wavelet packet decomposition is proposed in this paper. Above all, the collected pressure-difference fluctuation signals are decomposed by the four-layer wavelet packet, and the decomposed signals in various frequency bands are obtained within the frequency domain. Then the wavelet packet energy eigenvectors of flow regimes are established. At last the wavelet packet energy eigenvectors are input into Elman neural network and flow regime intelligent identification can be performed.
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Lin, Chih-Min, and Enkh-Amgalan Boldbaatar. "Autolanding Control Using Recurrent Wavelet Elman Neural Network." IEEE Transactions on Systems, Man, and Cybernetics: Systems 45, no. 9 (September 2015): 1281–91. http://dx.doi.org/10.1109/tsmc.2015.2389752.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
Більше джерел

Дисертації з теми "Recurrent Elman neural network"

1

Gomes, Leonaldo da Silva. "Redes Neurais Aplicadas à InferÃncia dos Sinais de Controle de Dosagem de Coagulantes em uma ETA por FiltraÃÃo RÃpida." Universidade Federal do CearÃ, 2012. http://www.teses.ufc.br/tde_busca/arquivo.php?codArquivo=8105.

Повний текст джерела
Анотація:
Considerando a importÃncia do controle da coagulaÃÃo quÃmica para o processo de tratamento de Ãgua por filtraÃÃo rÃpida, esta dissertaÃÃo propÃe a aplicaÃÃo de redes neurais artificiais para inferÃncia dos sinais de controle de dosagem de coagulantes principal e auxiliar, no processo de coagulaÃÃo quÃmica em uma estaÃÃo de tratamento de Ãgua por filtraÃÃo rÃpida. Para tanto, foi feito uma anÃlise comparativa da aplicaÃÃo de modelos baseados em redes neurais do tipo: alimentada adiante focada atrasada no tempo (FTLFN); alimentada adiante atrasada no tempo distribuÃda (DTLFN); recorrente de Elman (ERN) e auto-regressiva nÃo-linear com entradas exÃgenas (NARX). Da anÃlise comparativa, o modelo baseado em redes NARX apresentou melhores resultados, evidenciando o potencial do modelo para uso em casos reais, o que contribuirà para a viabilizaÃÃo de projetos desta natureza em estaÃÃes de tratamento de Ãgua de pequeno porte.
Considering the importance of the chemical coagulation control for the water treatment by direct filtration, this work proposes the application of artificial neural networks for inference of dosage control signals of principal and auxiliary coagulant, in the chemical coagulation process in a water treatment plant by direct filtration. To that end, was made a comparative analysis of the application of models based on neural networks, such as: Focused Time Lagged Feedforward Network (FTLFN); Distributed Time Lagged Feedforward Network (DTLFN); Elman Recurrent Network (ERN) and Non-linear Autoregressive with exogenous inputs (NARX). From the comparative analysis, the model based on NARX networks showed better results, demonstrating the potential of the model for use in real cases, which will contribute to the viability of projects of this nature in small size water treatment plants.
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Křepský, Jan. "Rekurentní neuronové sítě v počítačovém vidění." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2011. http://www.nusl.cz/ntk/nusl-237029.

Повний текст джерела
Анотація:
The thesis concentrates on using recurrent neural networks in computer vision. The theoretical part describes the basic knowledge about artificial neural networks with focus on a recurrent architecture. There are presented some of possible applications of the recurrent neural networks which could be used for a solution of real problems. The practical part concentrates on face recognition from an image sequence using the Elman simple recurrent network. For training there are used the backpropagation and backpropagation through time algorithms.
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Дудник, Алексей Валентинович. "Оптимальные системы управления переходными процессами энергосберегающих объектов с переменными параметрами". Thesis, НТУ "ХПИ", 2016. http://repository.kpi.kharkov.ua/handle/KhPI-Press/22099.

Повний текст джерела
Анотація:
Диссертация на соискание ученой степени кандидата технических наук по специальности 05.13. 03 – системы и процессы управления. – Национальный технический университет "Харьковский политехнический институт", Харьков, 2016. Диссертация посвящена решению научно-практической задачи усовершенствования оптимальной по затратам энергии системы управления. В диссертационной работе рассмотрен метод оптимального управления в линейной системе при квадратичном критерии качества с учётом ограничений на управляемые координаты, применительно к разомкнутой системе. Показано, что существует шесть вариантов алгоритмов оптимального управления, в зависимости от сочетания ограничений, накладываемых на управляемые координаты. В зависимости от длительности процесса оптимального управления, алгоритмы располагаются в определённом порядке, относительно друг друга, образуя тем самым область решения задачи, ограниченную временем максимального быстродействия с одной стороны и временем минимальных затрат с другой. Математические зависимости для определения этих ограничений, а также границ соседних алгоритмов внутри этой области выведены в диссертации. В работе предложена функциональная схема двухуровневой системы оптимального управления. На верхнем уровне осуществляется выбор алгоритма оптимального управления и расчёт длительностей его интервалов. Основанием для вычислений служат внешние управляющие данные. При расчёте используются параметры объекта, идентифицированные на нижнем уровне. Контроллер нижнего уровня осуществляет выработку управляющих воздействий на объект, форма и длительность которых определена ЭВМ верхнего уровня. На контроллере нижнего уровня реализована система подчинённого регулирования, с целью удержания объекта на выбранной траектории оптимального движения в фазовом пространстве. Дополнительно, локальный контроллер реализовывает функции нейронного идентификатора параметров.
The thesis for scientific degree of candidate of technical sciences in the specialty 05.13.03 – control systems and processes. – National Technical University "Kharkov Polytechnic Institute", Kharkov, 2016. The thesis is devoted to solving scientific and practical problems of improvement of cost effective energy control system. In the thesis has given the method of optimal control in a linear open-loop system with quadratic criteria of quality. It is shown that there are six variants of the algorithms of optimal control, depending on the combination of constraints on the controlled axes. Depending on the duration, optimal control algorithms are arranged in a specific order, relative to each other, thereby forming a region of the problem solution by the time of maximum speed with one hand and minimal time costs with other. Mathematical dependences for definition of these limits and the borders of neighbour algorithms within this field are derived in the thesis. In the thesis is proposed a method for the identification of the drive parameters. This method based on recurrent neural network Elman. The mathematical relationship between the weight coefficients of the network layers and parameters of the engine allows using the network learning as a way of identification. The paper presents a functional diagram of a two-tier system of optimal control. On the upper level, there is a choice of algorithm of optimal control and calculation of intervals durations. The lower level controller performs the generation of control actions on the object, the shape and duration of which is determined the upper-level computer.
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Дудник, Олексій Валентинович. "Оптимальні системи керування перехідними процесами енергозаощаджуючих об'єктів зі змінними параметрами". Thesis, НТУ "ХПІ", 2016. http://repository.kpi.kharkov.ua/handle/KhPI-Press/22091.

Повний текст джерела
Анотація:
Дисертація на здобуття наукового ступеня кандидата технічних наук за спеціальністю 05.13. 03 – системи та процеси керування. – Національний технічний університет "Харківський політехнічний інститут", Харків, 2016. Дисертація присвячена вирішенню науково-практичної задачі вдосконалення оптимальною за витратами енергії системи керування. У дисертаційній роботі розглянуто метод оптимального керування в лінійній системі при квадратичному критерії якості з урахуванням обмежень на керовані координати, стосовно до розімкнутої системи. Показано, що існує шість варіантів алгоритмів оптимального керування, в залежності від поєднання обмежень, що накладаються на керовані координати. В залежності від тривалості процесу оптимального керування, алгоритми розташовуються у певному порядку, відносно один одного, утворюючи область рішення, обмежену часом максимальної швидкодії з одного боку і часом мінімальних витрат з іншого. Математичні залежності для визначення цих обмежень, а також кордонів сусідніх алгоритмів всередині цієї області виведені в дисертації. В дисертації запропоновано метод ідентифікації параметрів позиційного приводу, заснований на рекурентної нейронної мережі Елмана. Математичний зв'язок між ваговими коефіцієнтами рекурентного і зовнішнього шарів мережі з параметрами двигуна дозволяє застосувати здатність мережі до навчання як спосіб ідентифікації. В роботі запропонована функціональна схема дворівневої системи оптимального керування. На верхньому рівні здійснюється вибір алгоритму оптимального керування і розрахунок тривалості його інтервалів. Контролер нижнього рівня здійснює вироблення керуючих впливів на об'єкт, форма і тривалість яких визначена ЕОМ верхнього рівня.
The thesis for scientific degree of candidate of technical sciences in the specialty 05.13.03 – control systems and processes. – National Technical University "Kharkov Polytechnic Institute", Kharkov, 2016. The thesis is devoted to solving scientific and practical problems of improvement of cost effective energy control system. In the thesis has given the method of optimal control in a linear open-loop system with quadratic criteria of quality. It is shown that there are six variants of the algorithms of optimal control, depending on the combination of constraints on the controlled axes. Depending on the duration, optimal control algorithms are arranged in a specific order, relative to each other, thereby forming a region of the problem solution by the time of maximum speed with one hand and minimal time costs with other. Mathematical dependences for definition of these limits and the borders of neighbour algorithms within this field are derived in the thesis. In the thesis is proposed a method for the identification of the drive parameters. This method based on recurrent neural network Elman. The mathematical relationship between the weight coefficients of the network layers and parameters of the engine allows using the network learning as a way of identification. The paper presents a functional diagram of a two-tier system of optimal control. On the upper level, there is a choice of algorithm of optimal control and calculation of intervals durations. The lower level controller performs the generation of control actions on the object, the shape and duration of which is determined the upper-level computer.
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Tekin, Mim Kemal. "Vehicle Path Prediction Using Recurrent Neural Network." Thesis, Linköpings universitet, Statistik och maskininlärning, 2020. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-166134.

Повний текст джерела
Анотація:
Vehicle Path Prediction can be used to support Advanced Driver Assistance Systems (ADAS) that covers different technologies like Autonomous Braking System, Adaptive Cruise Control, etc. In this thesis, the vehicle’s future path, parameterized as 5 coordinates along the path, is predicted by using only visual data collected by a front vision sensor. This approach provides cheaper application opportunities without using different sensors. The predictions are done by deep convolutional neural networks (CNN) and the goal of the project is to use recurrent neural networks (RNN) and to investigate the benefits of using reccurence to the task. Two different approaches are used for the models. The first approach is a single-frame approach that makes predictions by using only one image frame as input and predicts the future location points of the car. The single-frame approach is the baseline model. The second approach is a sequential approach that enables the network the usage of historical information of previous image frames in order to predict the vehicle’s future path for the current frame. With this approach, the effect of using recurrence is investigated. Moreover, uncertainty is important for the model reliability. Having a small uncertainty in most of the predictions or having a high uncertainty in unfamiliar situations for the model will increase success of the model. In this project, the uncertainty estimation approach is based on capturing the uncertainty by following a method that allows to work on deep learning models. The uncertainty approach uses the same models that are defined by the first two approaches. Finally, the evaluation of the approaches are done by the mean absolute error and defining two different reasonable tolerance levels for the distance between the prediction path and the ground truth path. The difference between two tolerance levels is that the first one is a strict tolerance level and the the second one is a more relaxed tolerance level. When using strict tolerance level based on distances on test data, 36% of the predictions are accepted for single-frame model, 48% for the sequential model, 27% and 13% are accepted for single-frame and sequential models of uncertainty models. When using relaxed tolerance level on test data, 60% of the predictions are accepted by single-frame model, 67% for the sequential model, 65% and 53% are accepted for single-frame and sequential models of uncertainty models. Furthermore, by using stored information for each sequence, the methods are evaluated for different conditions such as day/night, road type and road cover. As a result, the sequential model outperforms in the majority of the evaluation results.
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Wen, Tsung-Hsien. "Recurrent neural network language generation for dialogue systems." Thesis, University of Cambridge, 2018. https://www.repository.cam.ac.uk/handle/1810/275648.

Повний текст джерела
Анотація:
Language is the principal medium for ideas, while dialogue is the most natural and effective way for humans to interact with and access information from machines. Natural language generation (NLG) is a critical component of spoken dialogue and it has a significant impact on usability and perceived quality. Many commonly used NLG systems employ rules and heuristics, which tend to generate inflexible and stylised responses without the natural variation of human language. However, the frequent repetition of identical output forms can quickly make dialogue become tedious for most real-world users. Additionally, these rules and heuristics are not scalable and hence not trivially extensible to other domains or languages. A statistical approach to language generation can learn language decisions directly from data without relying on hand-coded rules or heuristics, which brings scalability and flexibility to NLG. Statistical models also provide an opportunity to learn in-domain human colloquialisms and cross-domain model adaptations. A robust and quasi-supervised NLG model is proposed in this thesis. The model leverages a Recurrent Neural Network (RNN)-based surface realiser and a gating mechanism applied to input semantics. The model is motivated by the Long-Short Term Memory (LSTM) network. The RNN-based surface realiser and gating mechanism use a neural network to learn end-to-end language generation decisions from input dialogue act and sentence pairs; it also integrates sentence planning and surface realisation into a single optimisation problem. The single optimisation not only bypasses the costly intermediate linguistic annotations but also generates more natural and human-like responses. Furthermore, a domain adaptation study shows that the proposed model can be readily adapted and extended to new dialogue domains via a proposed recipe. Continuing the success of end-to-end learning, the second part of the thesis speculates on building an end-to-end dialogue system by framing it as a conditional generation problem. The proposed model encapsulates a belief tracker with a minimal state representation and a generator that takes the dialogue context to produce responses. These features suggest comprehension and fast learning. The proposed model is capable of understanding requests and accomplishing tasks after training on only a few hundred human-human dialogues. A complementary Wizard-of-Oz data collection method is also introduced to facilitate the collection of human-human conversations from online workers. The results demonstrate that the proposed model can talk to human judges naturally, without any difficulty, for a sample application domain. In addition, the results also suggest that the introduction of a stochastic latent variable can help the system model intrinsic variation in communicative intention much better.
Стилі APA, Harvard, Vancouver, ISO та ін.
7

He, Jian. "Adaptive power system stabilizer based on recurrent neural network." Thesis, National Library of Canada = Bibliothèque nationale du Canada, 1999. http://www.collectionscanada.ca/obj/s4/f2/dsk1/tape8/PQDD_0008/NQ38471.pdf.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Gangireddy, Siva Reddy. "Recurrent neural network language models for automatic speech recognition." Thesis, University of Edinburgh, 2017. http://hdl.handle.net/1842/28990.

Повний текст джерела
Анотація:
The goal of this thesis is to advance the use of recurrent neural network language models (RNNLMs) for large vocabulary continuous speech recognition (LVCSR). RNNLMs are currently state-of-the-art and shown to consistently reduce the word error rates (WERs) of LVCSR tasks when compared to other language models. In this thesis we propose various advances to RNNLMs. The advances are: improved learning procedures for RNNLMs, enhancing the context, and adaptation of RNNLMs. We learned better parameters by a novel pre-training approach and enhanced the context using prosody and syntactic features. We present a pre-training method for RNNLMs, in which the output weights of a feed-forward neural network language model (NNLM) are shared with the RNNLM. This is accomplished by first fine-tuning the weights of the NNLM, which are then used to initialise the output weights of an RNNLM with the same number of hidden units. To investigate the effectiveness of the proposed pre-training method, we have carried out text-based experiments on the Penn Treebank Wall Street Journal data, and ASR experiments on the TED lectures data. Across the experiments, we observe small but significant improvements in perplexity (PPL) and ASR WER. Next, we present unsupervised adaptation of RNNLMs. We adapted the RNNLMs to a target domain (topic or genre or television programme (show)) at test time using ASR transcripts from first pass recognition. We investigated two approaches to adapt the RNNLMs. In the first approach the forward propagating hidden activations are scaled - learning hidden unit contributions (LHUC). In the second approach we adapt all parameters of RNNLM.We evaluated the adapted RNNLMs by showing the WERs on multi genre broadcast speech data. We observe small (on an average 0.1% absolute) but significant improvements in WER compared to a strong unadapted RNNLM model. Finally, we present the context-enhancement of RNNLMs using prosody and syntactic features. The prosody features were computed from the acoustics of the context words and the syntactic features were from the surface form of the words in the context. We trained the RNNLMs with word duration, pause duration, final phone duration, syllable duration, syllable F0, part-of-speech tag and Combinatory Categorial Grammar (CCG) supertag features. The proposed context-enhanced RNNLMs were evaluated by reporting PPL and WER on two speech recognition tasks, Switchboard and TED lectures. We observed substantial improvements in PPL (5% to 15% relative) and small but significant improvements in WER (0.1% to 0.5% absolute).
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Bopaiah, Jeevith. "A recurrent neural network architecture for biomedical event trigger classification." UKnowledge, 2018. https://uknowledge.uky.edu/cs_etds/73.

Повний текст джерела
Анотація:
A “biomedical event” is a broad term used to describe the roles and interactions between entities (such as proteins, genes and cells) in a biological system. The task of biomedical event extraction aims at identifying and extracting these events from unstructured texts. An important component in the early stage of the task is biomedical trigger classification which involves identifying and classifying words/phrases that indicate an event. In this thesis, we present our work on biomedical trigger classification developed using the multi-level event extraction dataset. We restrict the scope of our classification to 19 biomedical event types grouped under four broad categories - Anatomical, Molecular, General and Planned. While most of the existing approaches are based on traditional machine learning algorithms which require extensive feature engineering, our model relies on neural networks to implicitly learn important features directly from the text. We use natural language processing techniques to transform the text into vectorized inputs that can be used in a neural network architecture. As per our knowledge, this is the first time neural attention strategies are being explored in the area of biomedical trigger classification. Our best results were obtained from an ensemble of 50 models which produced a micro F-score of 79.82%, an improvement of 1.3% over the previous best score.
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Amartur, Sundar C. "Competitive recurrent neural network model for clustering of multispectral data." Case Western Reserve University School of Graduate Studies / OhioLINK, 1995. http://rave.ohiolink.edu/etdc/view?acc_num=case1058445974.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
Більше джерел

Книги з теми "Recurrent Elman neural network"

1

Yi, Zhang, and K. K. Tan. Convergence Analysis of Recurrent Neural Networks (Network Theory and Applications). Springer, 2003.

Знайти повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Частини книг з теми "Recurrent Elman neural network"

1

Krichene, Emna, Youssef Masmoudi, Adel M. Alimi, Ajith Abraham, and Habib Chabchoub. "Forecasting Using Elman Recurrent Neural Network." In Advances in Intelligent Systems and Computing, 488–97. Cham: Springer International Publishing, 2017. http://dx.doi.org/10.1007/978-3-319-53480-0_48.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Bilski, Jarosław, and Jacek Smola̧g. "Parallel Realisation of the Recurrent Elman Neural Network Learning." In Artifical Intelligence and Soft Computing, 19–25. Berlin, Heidelberg: Springer Berlin Heidelberg, 2010. http://dx.doi.org/10.1007/978-3-642-13232-2_3.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

Nawi, Nazri Mohd, M. Z. Rehman, Norhamreeza Abdul Hamid, Abdullah Khan, Rashid Naseem, and Jamal Uddin. "Optimizing Weights in Elman Recurrent Neural Networks with Wolf Search Algorithm." In Advances in Intelligent Systems and Computing, 11–20. Cham: Springer International Publishing, 2016. http://dx.doi.org/10.1007/978-3-319-51281-5_2.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Wysocki, Antoni, and Maciej Ławryńczuk. "Two- and Three-Layer Recurrent Elman Neural Networks as Models of Dynamic Processes." In Challenges in Automation, Robotics and Measurement Techniques, 165–75. Cham: Springer International Publishing, 2016. http://dx.doi.org/10.1007/978-3-319-29357-8_15.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Zhang, Zhong-Yuan. "Recurrent Neural Network." In Encyclopedia of Systems Biology, 1824–25. New York, NY: Springer New York, 2013. http://dx.doi.org/10.1007/978-1-4419-9863-7_418.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Ayyadevara, V. Kishore. "Recurrent Neural Network." In Pro Machine Learning Algorithms, 217–57. Berkeley, CA: Apress, 2018. http://dx.doi.org/10.1007/978-1-4842-3564-5_10.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Nakayama, Hideki. "Recurrent Neural Network." In Computer Vision, 1051–58. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-63416-2_855.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Nakayama, Hideki. "Recurrent Neural Network." In Computer Vision, 1–7. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-03243-2_855-1.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Kanagachidambaresan, G. R., Adarsha Ruwali, Debrup Banerjee, and Kolla Bhanu Prakash. "Recurrent Neural Network." In Programming with TensorFlow, 53–61. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-57077-4_7.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Long, Liangqu, and Xiangming Zeng. "Recurrent Neural Network." In Beginning Deep Learning with TensorFlow, 461–517. Berkeley, CA: Apress, 2022. http://dx.doi.org/10.1007/978-1-4842-7915-1_11.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Тези доповідей конференцій з теми "Recurrent Elman neural network"

1

Mat Darus, I. Z., M. O. Tokhi, and S. Z. Mohd. Hashim. "Non-Linear System Identification of Flexible Plate Structures Using Neural Networks." In ASME 7th Biennial Conference on Engineering Systems Design and Analysis. ASMEDC, 2004. http://dx.doi.org/10.1115/esda2004-58200.

Повний текст джерела
Анотація:
This paper investigates the utilisation of feedforward and recurrent neural networks for dynamic modelling of a flexible plate structure. Neuro-modelling techniques are used for non-parametric identification of the flexible plate structure based on one-step-ahead prediction. A multi layer perceptron (MLP) and Elman neural networks are designed to characterise the dynamic behaviour of the flexible plate. Results of the modelling techniques are validated through a range of tests including input/output mapping, training and test validation, mean-squared error and correlation tests. Results are presented in both time and frequency domains. Comparative performance assessments of both neuro-modelling approaches in terms of mean-squared error and estimation of the resonance modes of the system are carried out. It is noted that both techniques have been able to detect the first five vibration modes of the system successfully. Investigations also signify the advantage of a recurrent Elman network over an MLP feedforward network in modelling the flexible plate structure.
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Nikolaev, Nikolay Y., Derrick Mirikitani, and Evgueni Smirnov. "Unscented grid filtering and elman recurrent networks." In 2010 International Joint Conference on Neural Networks (IJCNN). IEEE, 2010. http://dx.doi.org/10.1109/ijcnn.2010.5596830.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

N., Siddarameshwara, Anup Yelamali, and Kshitiz Byahatti. "Electricity Short Term Load Forecasting Using Elman Recurrent Neural Network." In 2010 International Conference on Advances in Recent Technologies in Communication and Computing (ARTCom). IEEE, 2010. http://dx.doi.org/10.1109/artcom.2010.44.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Feng, Chenghao, Zheng Zhao, Zhoufeng Ying, Jiaqi Gu, David Z. Pan, and Ray T. Chen. "Compact Design of On-chip Elman Optical Recurrent Neural Network." In CLEO: Applications and Technology. Washington, D.C.: OSA, 2020. http://dx.doi.org/10.1364/cleo_at.2020.jth2b.8.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Aytenfsu, Samuel A., Asrat M. Beyene, and Tameru H. Getaneh. "Controlling the Interior of Greenhouses using Elman Recurrent Neural Network." In 2020 Fourth World Conference on Smart Trends in Systems Security and Sustainablity (WorldS4). IEEE, 2020. http://dx.doi.org/10.1109/worlds450073.2020.9210373.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
6

Toha, S. F., and M. O. Tokhi. "MLP and Elman recurrent neural network modelling for the TRMS." In 2008 7th IEEE International Conference on Cybernetic Intelligent Systems (CIS). IEEE, 2008. http://dx.doi.org/10.1109/ukricis.2008.4798969.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
7

Yan, Jihong, and Pengxiang Wang. "Blade Material Fatigue Assessment Using Elman Neural Networks." In ASME 2007 International Mechanical Engineering Congress and Exposition. ASMEDC, 2007. http://dx.doi.org/10.1115/imece2007-43311.

Повний текст джерела
Анотація:
Material degradation evaluation and life prediction of major components such as blades, rotors, valves of steam turbines not only guarantees reliable, efficient and continuous operation of electric plants, but also offers the promise of substantially reducing the cost of repair and replacement of defective parts, and may even result in saving lives. In this paper, a recurrent neural network based strategy was developed for material degradation assessment and fatigue damage propagation prediction. Two Elman Neural Networks were developed for fatigue severity assessment and trend prediction correspondingly. The performance of the proposed prognostic methodology was evaluated by using blade material fatigue data collected from a material testing system. The prognostic method is found to be a reliable and robust material fatigue predictor.
Стилі APA, Harvard, Vancouver, ISO та ін.
8

Dillak, Rocky Yefrenes, Sumartini Dana, and Marthen Beily. "Face recognition using 3D GLCM and Elman Levenberg recurrent Neural Network." In 2016 International Seminar on Application for Technology of Information and Communication (ISemantic). IEEE, 2016. http://dx.doi.org/10.1109/isemantic.2016.7873829.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
9

Wang, Limin, Xuming Han, and Ming Li. "Dynamic recurrent Elman neural network based on immune clonal selection algorithm." In Fourth International Conference on Digital Image Processing (ICDIP 2012), edited by Mohamed Othman, Sukumar Senthilkumar, and Xie Yi. SPIE, 2012. http://dx.doi.org/10.1117/12.956430.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
10

Dillak, Rocky Yefrenes, and Petrisia Widyasari Sudarmadji. "Cervical Cancer Classification Using Elman Recurrent Neural Network and Genetic Algorithm." In 2021 5th International Conference on Informatics and Computational Sciences (ICICoS). IEEE, 2021. http://dx.doi.org/10.1109/icicos53627.2021.9651852.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.

Звіти організацій з теми "Recurrent Elman neural network"

1

Brabel, Michael J. Basin Sculpting a Hybrid Recurrent Feedforward Neural Network. Fort Belvoir, VA: Defense Technical Information Center, January 1998. http://dx.doi.org/10.21236/ada336386.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
2

Bodruzzaman, M., and M. A. Essawy. Iterative prediction of chaotic time series using a recurrent neural network. Quarterly progress report, January 1, 1995--March 31, 1995. Office of Scientific and Technical Information (OSTI), March 1996. http://dx.doi.org/10.2172/283610.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
3

BARKHATOV, NIKOLAY, and SERGEY REVUNOV. A software-computational neural network tool for predicting the electromagnetic state of the polar magnetosphere, taking into account the process that simulates its slow loading by the kinetic energy of the solar wind. SIB-Expertise, December 2021. http://dx.doi.org/10.12731/er0519.07122021.

Повний текст джерела
Анотація:
The auroral activity indices AU, AL, AE, introduced into geophysics at the beginning of the space era, although they have certain drawbacks, are still widely used to monitor geomagnetic activity at high latitudes. The AU index reflects the intensity of the eastern electric jet, while the AL index is determined by the intensity of the western electric jet. There are many regression relationships linking the indices of magnetic activity with a wide range of phenomena observed in the Earth's magnetosphere and atmosphere. These relationships determine the importance of monitoring and predicting geomagnetic activity for research in various areas of solar-terrestrial physics. The most dramatic phenomena in the magnetosphere and high-latitude ionosphere occur during periods of magnetospheric substorms, a sensitive indicator of which is the time variation and value of the AL index. Currently, AL index forecasting is carried out by various methods using both dynamic systems and artificial intelligence. Forecasting is based on the close relationship between the state of the magnetosphere and the parameters of the solar wind and the interplanetary magnetic field (IMF). This application proposes an algorithm for describing the process of substorm formation using an instrument in the form of an Elman-type ANN by reconstructing the AL index using the dynamics of the new integral parameter we introduced. The use of an integral parameter at the input of the ANN makes it possible to simulate the structure and intellectual properties of the biological nervous system, since in this way an additional realization of the memory of the prehistory of the modeled process is provided.
Стилі APA, Harvard, Vancouver, ISO та ін.
4

Mohanty, Subhasish, and Joseph Listwan. Development of Digital Twin Predictive Model for PWR Components: Updates on Multi Times Series Temperature Prediction Using Recurrent Neural Network, DMW Fatigue Tests, System Level Thermal-Mechanical-Stress Analysis. Office of Scientific and Technical Information (OSTI), September 2021. http://dx.doi.org/10.2172/1822853.

Повний текст джерела
Стилі APA, Harvard, Vancouver, ISO та ін.
5

Engel, Bernard, Yael Edan, James Simon, Hanoch Pasternak, and Shimon Edelman. Neural Networks for Quality Sorting of Agricultural Produce. United States Department of Agriculture, July 1996. http://dx.doi.org/10.32747/1996.7613033.bard.

Повний текст джерела
Анотація:
The objectives of this project were to develop procedures and models, based on neural networks, for quality sorting of agricultural produce. Two research teams, one in Purdue University and the other in Israel, coordinated their research efforts on different aspects of each objective utilizing both melons and tomatoes as case studies. At Purdue: An expert system was developed to measure variances in human grading. Data were acquired from eight sensors: vision, two firmness sensors (destructive and nondestructive), chlorophyll from fluorescence, color sensor, electronic sniffer for odor detection, refractometer and a scale (mass). Data were analyzed and provided input for five classification models. Chlorophyll from fluorescence was found to give the best estimation for ripeness stage while the combination of machine vision and firmness from impact performed best for quality sorting. A new algorithm was developed to estimate and minimize training size for supervised classification. A new criteria was established to choose a training set such that a recurrent auto-associative memory neural network is stabilized. Moreover, this method provides for rapid and accurate updating of the classifier over growing seasons, production environments and cultivars. Different classification approaches (parametric and non-parametric) for grading were examined. Statistical methods were found to be as accurate as neural networks in grading. Classification models by voting did not enhance the classification significantly. A hybrid model that incorporated heuristic rules and either a numerical classifier or neural network was found to be superior in classification accuracy with half the required processing of solely the numerical classifier or neural network. In Israel: A multi-sensing approach utilizing non-destructive sensors was developed. Shape, color, stem identification, surface defects and bruises were measured using a color image processing system. Flavor parameters (sugar, acidity, volatiles) and ripeness were measured using a near-infrared system and an electronic sniffer. Mechanical properties were measured using three sensors: drop impact, resonance frequency and cyclic deformation. Classification algorithms for quality sorting of fruit based on multi-sensory data were developed and implemented. The algorithms included a dynamic artificial neural network, a back propagation neural network and multiple linear regression. Results indicated that classification based on multiple sensors may be applied in real-time sorting and can improve overall classification. Advanced image processing algorithms were developed for shape determination, bruise and stem identification and general color and color homogeneity. An unsupervised method was developed to extract necessary vision features. The primary advantage of the algorithms developed is their ability to learn to determine the visual quality of almost any fruit or vegetable with no need for specific modification and no a-priori knowledge. Moreover, since there is no assumption as to the type of blemish to be characterized, the algorithm is capable of distinguishing between stems and bruises. This enables sorting of fruit without knowing the fruits' orientation. A new algorithm for on-line clustering of data was developed. The algorithm's adaptability is designed to overcome some of the difficulties encountered when incrementally clustering sparse data and preserves information even with memory constraints. Large quantities of data (many images) of high dimensionality (due to multiple sensors) and new information arriving incrementally (a function of the temporal dynamics of any natural process) can now be processed. Furhermore, since the learning is done on-line, it can be implemented in real-time. The methodology developed was tested to determine external quality of tomatoes based on visual information. An improved model for color sorting which is stable and does not require recalibration for each season was developed for color determination. Excellent classification results were obtained for both color and firmness classification. Results indicted that maturity classification can be obtained using a drop-impact and a vision sensor in order to predict the storability and marketing of harvested fruits. In conclusion: We have been able to define quantitatively the critical parameters in the quality sorting and grading of both fresh market cantaloupes and tomatoes. We have been able to accomplish this using nondestructive measurements and in a manner consistent with expert human grading and in accordance with market acceptance. This research constructed and used large databases of both commodities, for comparative evaluation and optimization of expert system, statistical and/or neural network models. The models developed in this research were successfully tested, and should be applicable to a wide range of other fruits and vegetables. These findings are valuable for the development of on-line grading and sorting of agricultural produce through the incorporation of multiple measurement inputs that rapidly define quality in an automated manner, and in a manner consistent with the human graders and inspectors.
Стилі APA, Harvard, Vancouver, ISO та ін.
Також вас можуть зацікавити розширені добірки на тему "Recurrent Elman neural network" для конкретних типів джерел:
Статті в журналах Дисертації
Ми пропонуємо знижки на всі преміум-плани для авторів, чиї праці увійшли до тематичних добірок літератури. Зв'яжіться з нами, щоб отримати унікальний промокод!

До бібліографії