Informacja

Drogi użytkowniku, aplikacja do prawidłowego działania wymaga obsługi JavaScript. Proszę włącz obsługę JavaScript w Twojej przeglądarce.

English (EN)·Polski (PL)·Yкраїнський (UK)
Przejdź do strony domowej biblioteki Centralna Biblioteka Wojskowa Link otwiera się w nowym oknie Logo biblioteki Prolib Integro - strona głównaCentralna Biblioteka Wojskowa

Wyszukujesz frazę "learning machines" wg kryterium: Temat

  Lista filtrów
Wyrównaj
    Wyświetlanie 1-11 z 11
    Tytuł:
    An optimized parallel implementation of non-iteratively trained recurrent neural networks
    Autorzy:
    El Zini, Julia
    Rizk, Yara
    Awad, Mariette
    Powiązania:
    https://bibliotekanauki.pl/articles/2031147.pdf
    Data publikacji:
    2021
    Wydawca:
    Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
    Tematy:
    GPU implementation
    parallelization
    Recurrent Neural Network
    RNN
    Long-short Term Memory
    LSTM
    Gated Recurrent Unit
    GRU
    Extreme Learning Machines
    ELM
    non-iterative training
    Opis:
    Recurrent neural networks (RNN) have been successfully applied to various sequential decision-making tasks, natural language processing applications, and time-series predictions. Such networks are usually trained through back-propagation through time (BPTT) which is prohibitively expensive, especially when the length of the time dependencies and the number of hidden neurons increase. To reduce the training time, extreme learning machines (ELMs) have been recently applied to RNN training, reaching a 99% speedup on some applications. Due to its non-iterative nature, ELM training, when parallelized, has the potential to reach higher speedups than BPTT. In this work, we present Opt-PR-ELM, an optimized parallel RNN training algorithm based on ELM that takes advantage of the GPU shared memory and of parallel QR factorization algorithms to efficiently reach optimal solutions. The theoretical analysis of the proposed algorithm is presented on six RNN architectures, including LSTM and GRU, and its performance is empirically tested on ten time-series prediction applications. Opt- PR-ELM is shown to reach up to 461 times speedup over its sequential counterpart and to require up to 20x less time to train than parallel BPTT. Such high speedups over new generation CPUs are extremely crucial in real-time applications and IoT environments.
    Źródło:
    Journal of Artificial Intelligence and Soft Computing Research; 2021, 11, 1; 33-50
    2083-2567
    2449-6499
    Pojawia się w:
    Journal of Artificial Intelligence and Soft Computing Research
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Assessment of Approaches for the Extraction of Building Footprints from Pléiades Images
    Autorzy:
    Taha, Lamyaa Gamal El-deen
    Ibrahim, Rania Elsayed
    Powiązania:
    https://bibliotekanauki.pl/articles/1837996.pdf
    Data publikacji:
    2021
    Wydawca:
    Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
    Tematy:
    ensemble classifiers
    machine learning
    random forest
    maximum likelihood
    support vector machines
    backpropagation
    image classification
    Opis:
    The Marina area represents an official new gateway of entry to Egypt and the development of infrastructure is proceeding rapidly in this region. The objective of this research is to obtain building data by means of automated extraction from Pléiades satellite images. This is due to the need for efficient mapping and updating of geodatabases for urban planning and touristic development. It compares the performance of random forest algorithm to other classifiers like maximum likelihood, support vector machines, and backpropagation neural networks over the well-organized buildings which appeared in the satellite images. Images were subsequently classified into two classes: buildings and non-buildings. In addition, basic morphological operations such as opening and closing were used to enhance the smoothness and connectedness of the classified imagery. The overall accuracy for random forest, maximum likelihood, support vector machines, and backpropagation were 97%, 95%, 93% and 92% respectively. It was found that random forest was the best option, followed by maximum likelihood, while the least effective was the backpropagation neural network. The completeness and correctness of the detected buildings were evaluated. Experiments confirmed that the four classification methods can effectively and accurately detect 100% of buildings from very high-resolution images. It is encouraged to use machine learning algorithms for object detection and extraction from very high-resolution images.
    Źródło:
    Geomatics and Environmental Engineering; 2021, 15, 4; 101-116
    1898-1135
    Pojawia się w:
    Geomatics and Environmental Engineering
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Efficient heart disease diagnosis based on twin support vector machine
    Autorzy:
    Brik, Youcef
    Djerioui, Mohamed
    Attallah, Bilal
    Powiązania:
    https://bibliotekanauki.pl/articles/1840868.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Polskie Towarzystwo Diagnostyki Technicznej PAN
    Tematy:
    heart diseases
    medical data
    diagnostic
    machine learning
    twin support vector machines
    choroba serca
    diagnostyka
    uczenie maszynowe
    Opis:
    Heart disease is the leading cause of death in the world according to the World Health Organization (WHO). Researchers are more interested in using machine learning techniques to help medical staff diagnose or detect heart disease early. In this paper, we propose an efficient medical decision support system based on twin support vector machines (Twin-SVM) for heart disease diagnosing with binary target (i.e. presence or absence of disease). Unlike conventional support vector machines (SVM) that finds only one optimal hyperplane for separating the data points of first class from those of second class, which causes inaccurate decision, Twin-SVM finds two non-parallel hyper-planes so that each one is closer to the first class and is as far from the second class as possible. Our experiments are conducted on real heart disease dataset and many evaluation metrics have been considered to evaluate the performance of the proposed method. Furthermore, a comparison between the proposed method and several well-known classifiers as well as the state-of-the-art methods has been performed. The obtained results proved that our proposed method based on Twin-SVM technique gives promising performances better than the state-of-the-art. This improvement can seriously reduce time, materials, and labor in healthcare services while increasing the final decision accuracy.
    Źródło:
    Diagnostyka; 2021, 22, 3; 3-11
    1641-6414
    2449-5220
    Pojawia się w:
    Diagnostyka
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Automatic speech based emotion recognition using paralinguistics features
    Autorzy:
    Hook, J.
    Noroozi, F.
    Toygar, O.
    Anbarjafari, G.
    Powiązania:
    https://bibliotekanauki.pl/articles/200261.pdf
    Data publikacji:
    2019
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    random forests
    speech emotion recognition
    machine learning
    support vector machines
    lasy
    rozpoznawanie emocji mowy
    nauczanie maszynowe
    Opis:
    Affective computing studies and develops systems capable of detecting humans affects. The search for universal well-performing features for speech-based emotion recognition is ongoing. In this paper, a?small set of features with support vector machines as the classifier is evaluated on Surrey Audio-Visual Expressed Emotion database, Berlin Database of Emotional Speech, Polish Emotional Speech database and Serbian emotional speech database. It is shown that a?set of 87 features can offer results on-par with state-of-the-art, yielding 80.21, 88.6, 75.42 and 93.41% average emotion recognition rate, respectively. In addition, an experiment is conducted to explore the significance of gender in emotion recognition using random forests. Two models, trained on the first and second database, respectively, and four speakers were used to determine the effects. It is seen that the feature set used in this work performs well for both male and female speakers, yielding approximately 27% average emotion recognition in both models. In addition, the emotions for female speakers were recognized 18% of the time in the first model and 29% in the second. A?similar effect is seen with male speakers: the first model yields 36%, the second 28% a?verage emotion recognition rate. This illustrates the relationship between the constitution of training data and emotion recognition accuracy.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2019, 67, 3; 479-488
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Deep features extraction for robust fingerprint spoofing attack detection
    Autorzy:
    Souza de, Gustavo Botelho
    Silva Santos da, Daniel Felipe
    Gonçalves Pires, Rafael
    Nilceu Marana, Aparecido
    Paulo Papa, Joao
    Powiązania:
    https://bibliotekanauki.pl/articles/91725.pdf
    Data publikacji:
    2019
    Wydawca:
    Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
    Tematy:
    restricted Boltzmann Machines
    Deep Boltzmann Machines
    deep learning
    fingerprint spoofing detection
    biometrics
    Opis:
    Biometric systems have been widely considered as a synonym of security. However, in recent years, malicious people are violating them by presenting forged traits, such as gelatin fingers, to fool their capture sensors (spoofing attacks). To detect such frauds, methods based on traditional image descriptors have been developed, aiming liveness detection from the input data. However, due to their handcrafted approaches, most of them present low accuracy rates in challenging scenarios. In this work, we propose a novel method for fingerprint spoofing detection using the Deep Boltzmann Machines (DBM) for extraction of high-level features from the images. Such deep features are very discriminative, thus making complicated the task of forgery by attackers. Experiments show that the proposed method outperforms other state-of-the-art techniques, presenting high accuracy regarding attack detection
    Źródło:
    Journal of Artificial Intelligence and Soft Computing Research; 2019, 9, 1; 41-49
    2083-2567
    2449-6499
    Pojawia się w:
    Journal of Artificial Intelligence and Soft Computing Research
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Robustness of Support Vector Machines in Algorithmic Trading on Cryptocurrency Market
    Autorzy:
    Ślepaczuk, Robert
    Zenkova, Maryna
    Powiązania:
    https://bibliotekanauki.pl/articles/1356913.pdf
    Data publikacji:
    2019-08-07
    Wydawca:
    Uniwersytet Warszawski. Wydział Nauk Ekonomicznych
    Tematy:
    Machine learning
    support vector machines
    investment algorithm
    algorithmic trading
    strategy
    optimization
    cross-validation
    overfitting
    cryptocurrency market
    technical analysis
    meta parameters
    Opis:
    This study investigates the profitability of an algorithmic trading strategy based on training SVM model to identify cryptocurrencies with high or low predicted returns. A tail set is defined to be a group of coins whose volatility-adjusted returns are in the highest or the lowest quintile. Each cryptocurrency is represented by a set of six technical features. SVM is trained on historical tail sets and tested on the current data. The classifier is chosen to be a nonlinear support vector machine. The portfolio is formed by ranking coins using the SVM output. The highest ranked coins are used for long positions to be included in the portfolio for one reallocation period. The following metrics were used to estimate the portfolio profitability: %ARC (the annualized rate of change), %ASD (the annualized standard deviation of daily returns), MDD (the maximum drawdown coefficient), IR1, IR2 (the information ratio coefficients). The performance of the SVM portfolio is compared to the performance of the four benchmark strategies based on the values of the information ratio coefficient IR1, which quantifies the risk-weighted gain. The question of how sensitive the portfolio performance is to the parameters set in the SVM model is also addressed in this study.
    Źródło:
    Central European Economic Journal; 2018, 5, 52; 186 - 205
    2543-6821
    Pojawia się w:
    Central European Economic Journal
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Water demand forecasting using extreme learning machines
    Przewidywanie zapotrzebowania na wodę z użyciem technik uczenia maszynowego
    Autorzy:
    Tiwari, M.
    Adamowski, J.
    Adamowski, K.
    Powiązania:
    https://bibliotekanauki.pl/articles/292339.pdf
    Data publikacji:
    2016
    Wydawca:
    Instytut Technologiczno-Przyrodniczy
    Tematy:
    artificial neural networks
    bootstrap
    Canada
    extreme learning machines
    uncertainty
    water demand forecasting
    wavelets
    ekstremalne maszyny uczące się
    falki
    Kanada
    niepewność
    prognozowanie zapotrzebowania na wodę
    sztuczne sieci neuronowe
    Opis:
    The capacity of recently-developed extreme learning machine (ELM) modelling approaches in forecasting daily urban water demand from limited data, alone or in concert with wavelet analysis (W) or bootstrap (B) methods (i.e., ELM, ELMW, ELMB), was assessed, and compared to that of equivalent traditional artificial neural network-based models (i.e., ANN, ANNW, ANNB). The urban water demand forecasting models were developed using 3-year water demand and climate datasets for the city of Calgary, Alberta, Canada. While the hybrid ELMB and ANNB models provided satisfactory 1-day lead-time forecasts of similar accuracy, the ANNW and ELMW models provided greater accuracy, with the ELMW model outperforming the ANNW model. Significant improvement in peak urban water demand prediction was only achieved with the ELMW model. The superiority of the ELMW model over both the ANNW or ANNB models demonstrated the significant role of wavelet transformation in improving the overall performance of the urban water demand model.
    Oceniono zdolność modelowania z użyciem ekstremalnej maszyny uczącej się (ELM) stosowanej samodzielnie bądź w połączeniu z analizą falkową (W) lub metodami bootstrapowymi (B) (tzn. ELM, ELMW, ELMB) do przewidywania dobowego zapotrzebowania na wodę w mieście. Wyniki porównano z uzyskanymi tradycyjnymi metodami bazującymi na sztucznych sieciach neuronowych (tzn. ANN, ANNW, ANNB). Modele przewidujące zapotrzebowanie na wodę zbudowano z wykorzystaniem trzyletniego zapotrzebowania na wodę i zestawu danych klimatycznych dla miasta Calgary w kanadyjskiej prowincji Alberta. Hybrydowe modele ELMB i ANNB zapewniały satysfakcjonujące prognozy jednodniowe o podobnej dokładności, natomiast wyniki uzyskane z zastosowaniem modeli ELMW i ANNW były bardziej dokładne, przy czym model ELMW okazał się lepszy niż ANNW. Istotną poprawę prognozowania szczytowego zapotrzebowania na wodę w mieście uzyskano jedynie z zastosowaniem modelu ELMW. Wyższość modelu ELMW nad modelami ANNW czy ANNB dowodzi znaczącej roli transformacji falkowej w usprawnianiu działania modeli prognozujących zapotrzebowanie na wodę w mieście.
    Źródło:
    Journal of Water and Land Development; 2016, 28; 37-52
    1429-7426
    2083-4535
    Pojawia się w:
    Journal of Water and Land Development
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Improving the efficacy of automated fetal state assessment with fuzzy analysis of delivery outcome
    Autorzy:
    Czabanski, R.
    Jezewski, M.
    Horoba, K.
    Jezewski, J.
    Leski, J.
    Powiązania:
    https://bibliotekanauki.pl/articles/333655.pdf
    Data publikacji:
    2015
    Wydawca:
    Uniwersytet Śląski. Wydział Informatyki i Nauki o Materiałach. Instytut Informatyki. Zakład Systemów Komputerowych
    Tematy:
    fetal monitoring
    fuzzy inference
    support vector machines
    supervised learning
    monitorowanie płodu
    wnioskowanie rozmyte
    maszyna wektorów nośnych
    uczenie nadzorowane
    Opis:
    A number of methods of the qualitative assessment of fetal heart rate (FHR) signals are based on supervised learning. The classification methods based on the supervised learning require a set of training recordings accompanied by the reference interpretation. In the real data collections the class of signals related to fetal distress is usually under-represented. Too small percentage of distress patterns adversely affects the effectiveness of the automated evaluation of the fetal state. The paper presents a method of equalizing the class sizes based on the reference assessment of the fetal state with the fuzzy analysis of the newborn attributes. The supervised learning with increased number of the FHR signals, which are characterized by the highest rate of the fuzzy inference leads to significant increase of the efficacy of the qualitative assessment of the fetal state using the Lagrangian support vector machine.
    Źródło:
    Journal of Medical Informatics & Technologies; 2015, 24; 223-230
    1642-6037
    Pojawia się w:
    Journal of Medical Informatics & Technologies
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Graph-based generation of a meta-learning search space
    Autorzy:
    Jankowski, N.
    Powiązania:
    https://bibliotekanauki.pl/articles/330964.pdf
    Data publikacji:
    2012
    Wydawca:
    Uniwersytet Zielonogórski. Oficyna Wydawnicza
    Tematy:
    pozyskiwanie danych
    maszyna ucząca się
    inteligencja obliczeniowa
    meta learning
    data mining
    learning machines
    complexity of learning
    complexity of learning machines
    computational intelligence
    Opis:
    Meta-learning is becoming more and more important in current and future research concentrated around broadly defined data mining or computational intelligence. It can solve problems that cannot be solved by any single, specialized algorithm. The overall characteristic of each meta-learning algorithm mainly depends on two elements: the learning machine space and the supervisory procedure. The former restricts the space of all possible learning machines to a subspace to be browsed by a meta-learning algorithm. The latter determines the order of selected learning machines with a module responsible for machine complexity evaluation, organizes tests and performs analysis of results. In this article we present a framework for meta-learning search that can be seen as a method of sophisticated description and evaluation of functional search spaces of learning machine configurations used in meta-learning. Machine spaces will be defined by specially defined graphs where vertices are specialized machine configuration generators. By using such graphs the learning machine space may be modeled in a much more flexible way, depending on the characteristics of the problem considered and a priori knowledge. The presented method of search space description is used together with an advanced algorithm which orders test tasks according to their complexities.
    Źródło:
    International Journal of Applied Mathematics and Computer Science; 2012, 22, 3; 647-667
    1641-876X
    2083-8492
    Pojawia się w:
    International Journal of Applied Mathematics and Computer Science
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Clustering Methods Applied to Reduce the Training Sample Size in Support Vector Machines
    Wykorzystanie metod taksonomicznych do redukcji liczebności zbioru uczącego w metodzie wektorów nośnych
    Autorzy:
    Trzęsiok, Michał
    Powiązania:
    https://bibliotekanauki.pl/articles/905051.pdf
    Data publikacji:
    2009
    Wydawca:
    Uniwersytet Łódzki. Wydawnictwo Uniwersytetu Łódzkiego
    Tematy:
    support vector machines
    K-medoids
    machine learning
    Opis:
    Support vector machines belong to the group of methods of supervised learning. They generate non-linear models with good generalization abilities. The core of SVMs algorithm is the quadratic program which is solved for obtaining the optimal separating hyperplane. Because finding the solution of this quadratic program is computationally expensive, SVMs are not feasible for very large data sets. As a solution Wang, Wu and Zhang (2005) suggested to combine the AT-means clustering technique with SVMs to reduce the number of support vectors. The paper presents a common approach using K-medoids and compares it with the original SVMs.
    Metoda wektorów nośnych jest metodą dyskryminacji generującą nieliniowe modele o dużym stopniu uogólnienia (małych błędach klasyfikacji na zbiorach testowych). Jednak ze względu na dużą złożoność obliczeniową, związaną z koniecznością rozwiązania zadania optymalizacji wypukłej, które jest podstawowym elementem algorytmu metody, stosowanie metody, szczególnie w przypadku zbiorów uczących o dużej liczebności, nie zawsze jest możliwe. Złożoność obliczeniowa algorytmu metody wektorów nośnych zależy przede wszystkim od liczby obserwacji w zbiorze uczącym. Jako rozwiązanie tego problemu Wang, Wu i Zhang zaproponowali pogrupowanie danych ze zbioru uczącego za pomocą taksonomicznej metody AT-średnich i zastosowanie metody wektorów nośnych na dużo mniej licznym zbiorze środków ciężkości tak otrzymanych klas. W artykule przedstawiona została ocena analogicznego podejścia, wykorzystującego do grupowania metodę K-medoidów oraz porównanie z oryginalną metodą wektorów nośnych.
    Źródło:
    Acta Universitatis Lodziensis. Folia Oeconomica; 2009, 225
    0208-6018
    2353-7663
    Pojawia się w:
    Acta Universitatis Lodziensis. Folia Oeconomica
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Theoretical Concepts, Sources and Technical Background of E-learning
    Autorzy:
    Kapounová, Jana
    Kostolányová, Kateřina
    Pavlíček, Jiří
    Powiązania:
    https://bibliotekanauki.pl/articles/28765724.pdf
    Data publikacji:
    2006-03-31
    Wydawca:
    Wydawnictwo Adam Marszałek
    Tematy:
    Information and Communication Technology (ICT)
    programmed learning
    teaching machines
    courseware
    e-learning
    Learning Management System (LMS)
    learning object
    Opis:
    The topic Theoretical Concepts, Sources and Technical Background of E-learning is discussed in a project of the Czech Science Foundation. A research team from three Czech universities (University of Ostrava, Charles University in Prague and University of West Bohemia in Pilsen) is working on the project. Its aim is to summarise theoretical concepts, to analyse sources of content, to assess methodological background and to search for technical solutions how to transfer some titles of current courseware into electronic version and to evaluate the efficiency of procedure. The methodology of transformation can help authors of study materials (not only e-learning), they may benefit from old instructional programmes.
    Źródło:
    The New Educational Review; 2006, 8; 97-106
    1732-6729
    Pojawia się w:
    The New Educational Review
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
      Wyświetlanie 1-11 z 11

      Ta witryna wykorzystuje pliki cookies do przechowywania informacji na Twoim komputerze. Pliki cookies stosujemy w celu świadczenia usług na najwyższym poziomie, w tym w sposób dostosowany do indywidualnych potrzeb. Korzystanie z witryny bez zmiany ustawień dotyczących cookies oznacza, że będą one zamieszczane w Twoim komputerze. W każdym momencie możesz dokonać zmiany ustawień dotyczących cookies