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 "głębokie uczenie" wg kryterium: Temat

  Lista filtrów
Wyrównaj
    Wyświetlanie 1-14 z 14
    Tytuł:
    Deep learning: theory and practice
    Autorzy:
    Cichocki, A.
    Poggio, T.
    Osowski, S.
    Lempitsky, V.
    Powiązania:
    https://bibliotekanauki.pl/articles/202346.pdf
    Data publikacji:
    2018
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    deep learning
    networks
    theory
    practice
    uczenie głębokie
    sieci
    teoria
    praktyka
    Opis:
    This Special Section of the Bulletin of the Polish Academy of Sciences on Technical Sciences is devoted to theoretical aspects of deep machine learning as well as practical applications in some areas of signal and image processing, particularly in bioengineering.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 757-759
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Theory II: Deep learning and optimization
    Autorzy:
    Poggio, T.
    Liao, Q.
    Powiązania:
    https://bibliotekanauki.pl/articles/201787.pdf
    Data publikacji:
    2018
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    deep learning
    convolutional neural networks
    loss surface
    optimization
    uczenie głębokie
    sieć neuronowa
    optymalizacja
    Opis:
    The landscape of the empirical risk of overparametrized deep convolutional neural networks (DCNNs) is characterized with a mix of theory and experiments. In part A we show the existence of a large number of global minimizers with zero empirical error (modulo inconsistent equations). The argument which relies on the use of Bezout theorem is rigorous when the RELUs are replaced by a polynomial nonlinearity. We show with simulations that the corresponding polynomial network is indistinguishable from the RELU network. According to Bezout theorem, the global minimizers are degenerate unlike the local minima which in general should be non-degenerate. Further we experimentally analyzed and visualized the landscape of empirical risk of DCNNs on CIFAR-10 dataset. Based on above theoretical and experimental observations, we propose a simple model of the landscape of empirical risk. In part B, we characterize the optimization properties of stochastic gradient descent applied to deep networks. The main claim here consists of theoretical and experimental evidence for the following property of SGD: SGD concentrates in probability – like the classical Langevin equation – on large volume, ”flat” minima, selecting with high probability degenerate minimizers which are typically global minimizers.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 775-787
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Probabilistic adaptive computation time
    Autorzy:
    Figurnov, M.
    Sobolev, A.
    Vetrov, D.
    Powiązania:
    https://bibliotekanauki.pl/articles/201248.pdf
    Data publikacji:
    2018
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    deep learning
    probabilistic models
    adaptive computation time
    uczenie głębokie
    modele probabilistyczne
    adaptacyjny czas obliczeniowy
    Opis:
    We present a probabilistic model with discrete latent variables that control the computation time in deep learning models such as ResNets and LSTMs. A prior on the latent variables expresses the preference for faster computation. The amount of computation for an input is determined via amortized maximum a posteriori (MAP) inference. MAP inference is performed using a novel stochastic variational optimization method. The recently proposed adaptive computation time mechanism can be seen as an ad-hoc relaxation of this model. We demonstrate training using the general-purpose concrete relaxation of discrete variables. Evaluation on ResNet shows that our method matches the speed-accuracy trade-off of adaptive computation time, while allowing for evaluation with a simple deterministic procedure that has a lower memory footprint.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 811-820
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Comparative study on the classification methods for breast cancer diagnosis
    Autorzy:
    Qiu, Y.
    Zhou, G.
    Zhao, Q.
    Cichocki, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/200743.pdf
    Data publikacji:
    2018
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    breast cancer
    mammography
    DDSM
    comparative study
    deep learning
    rak piersi
    mammografia
    Badanie porównawcze
    uczenie głębokie
    Opis:
    Digital mammography is one of the most widely used approaches for breast cancer diagnosis. Many researchers have demonstrated the superiority of machine learning methods in breast cancer diagnosis using different mammography databases. Since these methods often have different pros and cons, which may confuse doctors and researchers, an elaborate comparison and examination among them is urgently needed for practical breast cancer diagnosis. In this study, we conducted a comprehensive comparative study of the state-of-the-art machine learning methods that are promising in breast cancer diagnosis. For this purpose we analyze the largest mammography diagnosis database: Digital Database for Screening Mammography (DDSM). We considered various approaches for feature extraction including principal component analysis (PCA), nonnegative matrix factorization (NMF), spatial-temporal discriminant analysis (STDA) and those for classification including linear discriminant analysis (LDA), random forests (RaF), k-nearest neighbors (kNN), as well as deep learning methods including convolutional neural networks (CNN) and stacked sparse autoencoder (SSAE). This paper can serve as a guideline and useful clues for doctors who are going to select machine learning methods for their breast cancer computer-aided diagnosis (CAD) systems as well for researchers interested in developing more reliable and efficient methods for breast cancer diagnosis.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 841-848
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Theory I: Deep networks and the curse of dimensionality
    Autorzy:
    Poggio, T.
    Liao, Q.
    Powiązania:
    https://bibliotekanauki.pl/articles/200623.pdf
    Data publikacji:
    2018
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    deep network
    shallow network
    convolutional neural network
    function approximation
    deep learning
    sieci neuronowe
    aproksymacja funkcji
    uczenie głębokie
    Opis:
    We review recent work characterizing the classes of functions for which deep learning can be exponentially better than shallow learning. Deep convolutional networks are a special case of these conditions, though weight sharing is not the main reason for their exponential advantage.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 761-773
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Multi-model hybrid ensemble weighted adaptive approach with decision level fusion for personalized affect recognition based on visual cues
    Autorzy:
    Jadhav, Nagesh
    Sugandhi, Rekha
    Powiązania:
    https://bibliotekanauki.pl/articles/2086876.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    deep learning
    convolution neural network
    emotion recognition
    transfer learning
    late fusion
    uczenie głębokie
    konwolucyjna sieć neuronowa
    rozpoznawanie emocji
    Opis:
    In the domain of affective computing different emotional expressions play an important role. To convey the emotional state of human emotions, facial expressions or visual cues are used as an important and primary cue. The facial expressions convey humans affective state more convincingly than any other cues. With the advancement in the deep learning techniques, the convolutional neural network (CNN) can be used to automatically extract the features from the visual cues; however variable sized and biased datasets are a vital challenge to be dealt with as far as implementation of deep models is concerned. Also, the dataset used for training the model plays a significant role in the retrieved results. In this paper, we have proposed a multi-model hybrid ensemble weighted adaptive approach with decision level fusion for personalized affect recognition based on the visual cues. We have used a CNN and pre-trained ResNet-50 model for the transfer learning. VGGFace model’s weights are used to initialize weights of ResNet50 for fine-tuning the model. The proposed system shows significant improvement in test accuracy in affective state recognition compared to the singleton CNN model developed from scratch or transfer learned model. The proposed methodology is validated on The Karolinska Directed Emotional Faces (KDEF) dataset with 77.85% accuracy. The obtained results are promising compared to the existing state of the art methods.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 6; e138819, 1--11
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Deep adversarial neural network for specific emitter identification under varying frequency
    Autorzy:
    Huang, Keju
    Yang, Junan
    Liu, Hui
    Hu, Pengjiang
    Powiązania:
    https://bibliotekanauki.pl/articles/2173603.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    specific emitter identification
    unsupervised domain adaptation
    transfer learning
    deep learning
    identyfikacja emitera konkretna
    adaptacja domeny nienadzorowana
    transfer uczenia się
    uczenie głębokie
    Opis:
    Specific emitter identification (SEI) is the process of identifying individual emitters by analyzing the radio frequency emissions, based on the fact that each device contains unique hardware imperfections. While the majority of previous research focuses on obtaining features that are discriminative, the reliability of the features is rarely considered. For example, since device characteristics of the same emitter vary when it is operating at different carrier frequencies, the performance of SEI approaches may degrade when the training data and the test data are collected from the same emitters with different frequencies. To improve performance of SEI under varying frequency, we propose an approach based on continuous wavelet transform (CWT) and domain adversarial neural network (DANN). The proposed approach exploits unlabeled test data in addition to labeled training data, in order to learn representations that are discriminative for individual emitters and invariant for varying frequencies. Experiments are conducted on received signals of five emitters under three carrier frequencies. The results demonstrate the superior performance of the proposed approach when the carrier frequencies of the training data and the test data differ.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 2; art. no. e136737
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    A BIM technology-based underwater structure damage identification and management method
    Autorzy:
    Li, Xiaofei
    Su, Rongrong
    Cheng, Peng
    Sun, Heming
    Meng, Qinghang
    Song, Taiyi
    Wei, Mengpu
    Zhang, Chen
    Powiązania:
    https://bibliotekanauki.pl/articles/2204531.pdf
    Data publikacji:
    2023
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    building information modeling
    underwater structural disease
    damage identification
    deep learning
    modelowanie informacji o budynku
    identyfikacja uszkodzeń
    uczenie głębokie
    uszkodzenie podwodnej konstrukcji
    Opis:
    With the continuous development of bridge technology, the condition assessment of large bridges has gradually attracted attention. Structural Health Monitoring (SHM) technology provides valuable information about a structure's existing health, keeping it safe and uninterrupted use under various operating conditions by mitigating risks and hazards on time. At the same time, the problem of bridge underwater structure disease is becoming more obvious, affecting the safe operation of the bridge structure. It is necessary to test the bridge’s underwater structure. This paper develops a bridge underwater structure health monitoring system by combining building information modeling (BIM) and an underwater structure damage algorithm. This paper is verified by multiple image recognition networks, and compared with the advantages of different networks, the YOLOV4 network is used as the main body to improve, and a lightweight convolutional neural network (Lite-yolov4) is built. At the same time, the accuracy of disease identification and the performance of each network are tested in various experimental environments, and the reliability of the underwater structure detection link is verified.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2023, 71, 2; art. no. e144602
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Selected technical issues of deep neural networks for image classification purposes
    Autorzy:
    Grochowski, Michał
    Kwasigroch, A.
    Mikołajczyk, A.
    Powiązania:
    https://bibliotekanauki.pl/articles/200871.pdf
    Data publikacji:
    2019
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    deep neural network
    deep learning
    image classification
    batch normalization
    transfer learning
    dropout
    sieć neuronowa
    klasyfikacja obrazów
    normalizacja
    transfer nauki
    uczenie głębokie
    Opis:
    In recent years, deep learning and especially deep neural networks (DNN) have obtained amazing performance on a variety of problems, in particular in classification or pattern recognition. Among many kinds of DNNs, the convolutional neural networks (CNN) are most commonly used. However, due to their complexity, there are many problems related but not limited to optimizing network parameters, avoiding overfitting and ensuring good generalization abilities. Therefore, a number of methods have been proposed by the researchers to deal with these problems. In this paper, we present the results of applying different, recently developed methods to improve deep neural network training and operating. We decided to focus on the most popular CNN structures, namely on VGG based neural networks: VGG16, VGG11 and proposed by us VGG8. The tests were conducted on a real and very important problem of skin cancer detection. A publicly available dataset of skin lesions was used as a benchmark. We analyzed the influence of applying: dropout, batch normalization, model ensembling, and transfer learning. Moreover, the influence of the type of activation function was checked. In order to increase the objectivity of the results, each of the tested models was trained 6 times and their results were averaged. In addition, in order to mitigate the impact of the selection of learning, test and validation sets, k-fold validation was applied.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2019, 67, 2; 363-376
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Deep adversarial neural network for specific emitter identification under varying frequency
    Autorzy:
    Huang, Keju
    Yang, Junan
    Liu, Hui
    Hu, Pengjiang
    Powiązania:
    https://bibliotekanauki.pl/articles/2128144.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    specific emitter identification
    unsupervised domain adaptation
    transfer learning
    deep learning
    identyfikacja emitera konkretna
    adaptacja domeny nienadzorowana
    transfer uczenia się
    uczenie głębokie
    Opis:
    Specific emitter identification (SEI) is the process of identifying individual emitters by analyzing the radio frequency emissions, based on the fact that each device contains unique hardware imperfections. While the majority of previous research focuses on obtaining features that are discriminative, the reliability of the features is rarely considered. For example, since device characteristics of the same emitter vary when it is operating at different carrier frequencies, the performance of SEI approaches may degrade when the training data and the test data are collected from the same emitters with different frequencies. To improve performance of SEI under varying frequency, we propose an approach based on continuous wavelet transform (CWT) and domain adversarial neural network (DANN). The proposed approach exploits unlabeled test data in addition to labeled training data, in order to learn representations that are discriminative for individual emitters and invariant for varying frequencies. Experiments are conducted on received signals of five emitters under three carrier frequencies. The results demonstrate the superior performance of the proposed approach when the carrier frequencies of the training data and the test data differ.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 2; e136737, 1--9
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Anonymous traffic classification based on three-dimensional Markov image and deep learning
    Autorzy:
    Tang, Xin
    Li, Huanzhou
    Zhang, Jian
    Tang, Zhangguo
    Wang, Han
    Cai, Cheng
    Powiązania:
    https://bibliotekanauki.pl/articles/27311448.pdf
    Data publikacji:
    2023
    Wydawca:
    Polska Akademia Nauk. Czasopisma i Monografie PAN
    Tematy:
    anonymous network
    traffic classification
    three-dimensional Markov image
    output self-attention
    deep learning
    sieć anonimowa
    klasyfikacja ruchu
    trójwymiarowy obraz Markowa
    samouwaga wyjściowa
    uczenie głębokie
    Opis:
    Illegal elements use the characteristics of an anonymous network hidden service mechanism to build a dark network and conduct various illegal activities, which brings a serious challenge to network security. The existing anonymous traffic classification methods suffer from cumbersome feature selection and difficult feature information extraction, resulting in low accuracy of classification. To solve this problem, a classification method based on three-dimensional Markov images and output self-attention convolutional neural network is proposed. This method first divides and cleans anonymous traffic data packets according to sessions, then converts the cleaned traffic data into three-dimensional Markov images according to the transition probability matrix of bytes, and finally inputs the images to the output self-attention convolution neural network to train the model and perform classification. The experimental results show that the classification accuracy and F1-score of the proposed method for Tor, I2P, Freenet, and ZeroNet can exceed 98.5%, and the average classification accuracy and F1-score for 8 kinds of user behaviors of each type of anonymous traffic can reach 93.7%. The proposed method significantly improves the classification effect of anonymous traffic compared with the existing methods.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2023, 71, 4; art. no. e145676
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Fast multispectral deep fusion networks
    Autorzy:
    Osin, V.
    Cichocki, A.
    Burnaev, E.
    Powiązania:
    https://bibliotekanauki.pl/articles/200648.pdf
    Data publikacji:
    2018
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    multispectral imaging
    data fusion
    deep learning
    convolutional network
    object detection
    image segmentation
    obrazowanie wielospektralne
    fuzja danych
    uczenie głębokie
    sieci splotowe
    wykrywanie obiektów
    segmentacja obrazu
    Opis:
    Most current state-of-the-art computer vision algorithms use images captured by cameras, which operate in the visible spectral range as input data. Thus, image recognition systems that build on top of those algorithms can not provide acceptable recognition quality in poor lighting conditions, e.g. during nighttime. Another significant limitation of such systems is high demand for computational resources, which makes them impossible to use on low-powered embedded systems without GPU support. This work attempts to create an algorithm for pattern recognition that will consolidate data from visible and infrared spectral ranges and allow near real-time performance on embedded systems with infrared and visible sensors. First, we analyze existing methods of combining data from different spectral ranges for object detection task. Based on the analysis, an architecture of a deep convolutional neural network is proposed for the fusion of multi-spectral data. This architecture is based on the single shot multi-box detection algorithm. Comparison analysis of the proposed architecture with previously proposed solutions for the multi-spectral object detection task shows comparable or better detection accuracy with previous algorithms and significant improvement of the running time on embedded systems. This study was conducted in collaboration with Philips Lighting Research Lab and solutions based on the proposed architecture will be used in image recognition systems for the next generation of intelligent lighting systems. Thus, the main scientific outcomes of this work include an algorithm for multi-spectral pattern recognition based on convolutional neural networks, as well as a modification of detection algorithms for working on embedded systems.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 875-889
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Deep learning for damaged tissue detection and segmentation in Ki-67 brain tumor specimens based on the U-net model
    Autorzy:
    Swiderska-Chadaj, Z.
    Markiewicz, T.
    Gallego, J.
    Bueno, G.
    Grala, B.
    Lorent, M.
    Powiązania:
    https://bibliotekanauki.pl/articles/202412.pdf
    Data publikacji:
    2018
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    damaged tissue regions detection
    artifacts detection
    deep learning
    Ki-67 staining specimens
    wykrywanie uszkodzonych regionów tkankowych
    wykrywanie artefaktów
    artefakt
    uczenie głębokie
    próbki barwiące Ki-67
    Opis:
    The pathologists follow a systematic and partially manual process to obtain histological tissue sections from the biological tissue extracted from patients. This process is far from being perfect and can introduce some errors in the quality of the tissue sections (distortions, deformations, folds and tissue breaks). In this paper, we propose a deep learning (DL) method for the detection and segmentation of these damaged regions in whole slide images (WSIs). The proposed technique is based on convolutional neural networks (CNNs) and uses the U-net model to achieve the pixel-wise segmentation of these unwanted regions. The results obtained show that this technique yields satisfactory results and can be applied as a pre-processing step for automatic WSI analysis in order to prevent the use of the damaged areas in the evaluation processes.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2018, 66, 6; 849-856
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Deep learning based Tamil Parts of Speech (POS) tagger
    Autorzy:
    Anbukkarasi, S.
    Varadhaganapathy, S.
    Powiązania:
    https://bibliotekanauki.pl/articles/2086879.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    POS tagging
    part of speech
    deep learning
    natural language processing
    BiLSTM
    Bi-directional long short term memory
    tagowanie POS
    części mowy
    uczenie głębokie
    przetwarzanie języka naturalnego
    Opis:
    This paper addresses the problem of part of speech (POS) tagging for the Tamil language, which is low resourced and agglutinative. POS tagging is the process of assigning syntactic categories for the words in a sentence. This is the preliminary step for many of the Natural Language Processing (NLP) tasks. For this work, various sequential deep learning models such as recurrent neural network (RNN), Long Short-Term Memory (LSTM), Gated Recurrent Unit (GRU) and Bi-directional Long Short-Term Memory (Bi-LSTM) were used at the word level. For evaluating the model, the performance metrics such as precision, recall, F1-score and accuracy were used. Further, a tag set of 32 tags and 225 000 tagged Tamil words was utilized for training. To find the appropriate hidden state, the hidden states were varied as 4, 16, 32 and 64, and the models were trained. The experiments indicated that the increase in hidden state improves the performance of the model. Among all the combinations, Bi-LSTM with 64 hidden states displayed the best accuracy (94%). For Tamil POS tagging, this is the initial attempt to be carried out using a deep learning model.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 6; e138820, 1--6
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
      Wyświetlanie 1-14 z 14

      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