Wszystkie pola: deep - Katalog OPAC zbiorów

Skocz do pozycji: 1.

Tytuł:: Improving accuracy of detecting dangerous objects with deep learning
Poprawa skuteczności wykrycia niebezpiecznych obiektów przy użyciu technik deep learning
Autorzy:: Zacniewski, A.
Powiązania:: https://bibliotekanauki.pl/articles/315763.pdf
Data publikacji:: 2016
Wydawca:: Instytut Naukowo-Wydawniczy "SPATIUM"
Tematy:: detecting dangerous objects
deep learning
detekcja niebezpiecznych obiektów
technika deep learning
Opis:: In this article, the problem of detecting dangerous objects with deep learning is presented. Convolutional Neural Networks are created with Python language ecosystem (Theano and Keras libraries), and then trained with different number of layers and different parameters. Accuracy of detection dangerous objects for artificial Neural Network with smaller number of layers is computed and obtained result is improved with deep learning. CIFAR-10 dataset is used due to useful classes included.
W artykule przedstawiono problem detekcji niebezpiecznych obiektów przy użyciu technik deep learning. Konwolucyjne sieci neuronowe tworzone są przy pomocy bibliotek języka Python takich jak Keras i Theano, a następnie trenowane są przy różnej liczbie warstw i z różnymi parametrami. Skuteczność detekcji niebezpiecznych obiektów dla małej liczby warstw sztucznej sieci neuronowej jest obliczana, a uzyskany wynik jest ulepszany przy użyciu technik deep learning. Zbiór danych CIFAR-10 został wykorzystany w badaniach z powodu dużej użyteczności występujących w nim klas.
Źródło:: Autobusy : technika, eksploatacja, systemy transportowe; 2016, 17, 12; 513-516
1509-5878
2450-7725
Pojawia się w:: Autobusy : technika, eksploatacja, systemy transportowe
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 2.

Tytuł:: Reliability of deep submicron MOSFETs
Autorzy:: Balestra, F.
Powiązania:: https://bibliotekanauki.pl/articles/307658.pdf
Data publikacji:: 2001
Wydawca:: Instytut Łączności - Państwowy Instytut Badawczy
Tematy:: bulk MOSFETs
SOI devices
deep submicron
transistors
reliability
Opis:: In this work, a review of the reliability of n- and p-channel Si and SOI MOSFETs as a function of gate length and temperature is given. The main hot carrier effects and degradation are compared for bulk and SOI devices in a wide range of gate length, down to deep submicron. The worst case aging, defice lifetime and maximum drain bias that can be applied are addressed. The physical mechanisms and the emergence of new phenomena at the origin of the degradation are studied for advanced MOS transistors. The impact of the substrate bias is also outlined.
Źródło:: Journal of Telecommunications and Information Technology; 2001, 1; 12-17
1509-4553
1899-8852
Pojawia się w:: Journal of Telecommunications and Information Technology
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 3.

Tytuł:: Laboratory investigations of deep-water wave transformation and stability
Autorzy:: Wilde, P.
Sobierajski, E.
Chybicki, W.
Sobczak, Ł.
Powiązania:: https://bibliotekanauki.pl/articles/240986.pdf
Data publikacji:: 2003
Wydawca:: Polska Akademia Nauk. Instytut Budownictwa Wodnego PAN
Tematy:: laboratory investigations
deep-water wave transformation
deep-water wave stability
Opis:: The authors performed laboratory investigations and the analysis of the transformation of deep-water waves in the flume of the Institute of Hydro-Engineering. Special wave trains were generated by our piston-type wavemaker. Due to the transformation the wave profiles changed along the path of propagation. At first, the changes appeared at the ends of the wave train. Far from the generator they intruded into the middle interval of initially regular waves. Finally, the whole wave train consisted of a set of irregular groups. To study the instability problem the wave trains were modulated by superposition of wave groups with very small amplitudes. The number of waves in a group was a very important parameter. When the number was proper, even small amplitudes of modulation resulted in strong development of amplitudes of wave groups. In our theoretical analysis the non-linear Schroedinger equation was used. The comparison of laboratory and theoretical results proved that this equation is useful but it does not describe the phenomenon in the best way. There have been many attempts to construct a numerical procedure that describes the propagation of water waves. Very often the numerical algorithm is not stable and the results of calculation diverge from the expected behaviour. The authors believe that in many cases the instability is due to the physical loss of stability of the wave train and thus it is necessary to have a good understanding of the physics of the studied motion.
Źródło:: Archives of Hydro-Engineering and Environmental Mechanics; 2003, 50, 3; 287-313
1231-3726
Pojawia się w:: Archives of Hydro-Engineering and Environmental Mechanics
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 4.

Tytuł:: Deep reinforcement learning overview of the state of the art
Autorzy:: Fenjiro, Y.
Benbrahim, H.
Powiązania:: https://bibliotekanauki.pl/articles/384788.pdf
Data publikacji:: 2018
Wydawca:: Sieć Badawcza Łukasiewicz - Przemysłowy Instytut Automatyki i Pomiarów
Tematy:: reinforcement learning
deep learning
convolutional network
recurrent network
deep reinforcement learning
Opis:: Artificial intelligence has made big steps forward with reinforcement learning (RL) in the last century, and with the advent of deep learning (DL) in the 90s, especially, the breakthrough of convolutional networks in computer vision field. The adoption of DL neural networks in RL, in the first decade of the 21 century, led to an end-toend framework allowing a great advance in human-level agents and autonomous systems, called deep reinforcement learning (DRL). In this paper, we will go through the development Timeline of RL and DL technologies, describing the main improvements made in both fields. Then, we will dive into DRL and have an overview of the state-ofthe- art of this new and promising field, by browsing a set of algorithms (Value optimization, Policy optimization and Actor-Critic), then, giving an outline of current challenges and real-world applications, along with the hardware and frameworks used. In the end, we will discuss some potential research directions in the field of deep RL, for which we have great expectations that will lead to a real human level of intelligence.
Źródło:: Journal of Automation Mobile Robotics and Intelligent Systems; 2018, 12, 3; 20-39
1897-8649
2080-2145
Pojawia się w:: Journal of Automation Mobile Robotics and Intelligent Systems
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 5.

Tytuł:: Characterization of symbolic rules embedded in deep DIMLP networks : a challenge to transparency of deep learning
Autorzy:: Bologna, G.
Hayashi, Y.
Powiązania:: https://bibliotekanauki.pl/articles/91545.pdf
Data publikacji:: 2017
Wydawca:: Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:: ensemble
Deep Learning
rule extraction
feature detectors
Opis:: Rule extraction from neural networks is a fervent research topic. In the last 20 years many authors presented a number of techniques showing how to extract symbolic rules from Multi Layer Perceptrons (MLPs). Nevertheless, very few were related to ensembles of neural networks and even less for networks trained by deep learning. On several datasets we performed rule extraction from ensembles of Discretized Interpretable Multi Layer Perceptrons (DIMLP), and DIMLPs trained by deep learning. The results obtained on the Thyroid dataset and the Wisconsin Breast Cancer dataset show that the predictive accuracy of the extracted rules compare very favorably with respect to state of the art results. Finally, in the last classification problem on digit recognition, generated rules from the MNIST dataset can be viewed as discriminatory features in particular digit areas. Qualitatively, with respect to rule complexity in terms of number of generated rules and number of antecedents per rule, deep DIMLPs and DIMLPs trained by arcing give similar results on a binary classification problem involving digits 5 and 8. On the whole MNIST problem we showed that it is possible to determine the feature detectors created by neural networks and also that the complexity of the extracted rulesets can be well balanced between accuracy and interpretability.
Źródło:: Journal of Artificial Intelligence and Soft Computing Research; 2017, 7, 4; 265-286
2083-2567
2449-6499
Pojawia się w:: Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 6.

Tytuł:: Głębokie wykopy 2016
Deep excavations 2016
Autorzy:: Rychlewski, P.
Powiązania:: https://bibliotekanauki.pl/articles/364283.pdf
Data publikacji:: 2016
Wydawca:: Nowoczesne Budownictwo Inżynieryjne
Tematy:: seminarium
relacja
głębokie wykopy
geotechnika
seminar
relation
deep excavations
geotechnics
Opis:: 3 marca br. Instytut Badawczy Dróg i Mostów oraz Polskie Zrzeszenie Wykonawców Fundamentów Specjalnych zorganizowały w Warszawie XV seminarium geotechniczne Głębokie wykopy 2016.
On 3 March 2016, the research Institute of Roads and Bridges and the polish Association for Special Foundations Contractors organized the fifteenth geotechnical seminar "Deep Excavations 2016" held in Warsaw.
Źródło:: Nowoczesne Budownictwo Inżynieryjne; 2016, 3; 60
1734-6681
Pojawia się w:: Nowoczesne Budownictwo Inżynieryjne
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 7.

Tytuł:: A novel deep neural network that uses space-time features for tracking and recognizing a moving object
Autorzy:: Chang, O.
Constante, P.
Gordon, A.
Singaña, M.
Powiązania:: https://bibliotekanauki.pl/articles/91702.pdf
Data publikacji:: 2017
Wydawca:: Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
Tematy:: deep architectures
deep learning
artificial vision
Opis:: This work proposes a deep neural net (DNN) that accomplishes the reliable visual recognition of a chosen object captured with a webcam and moving in a 3D space. Autoencoding and substitutional reality are used to train a shallow net until it achieves zero tracking error in a discrete ambient. This trained individual is set to work in a real world closed loop system where images coming from a webcam produce displacement information for a moving region of interest (ROI) inside the own image. This loop gives rise to an emergent tracking behavior which creates a self-maintain flow of compressed space-time data. Next, short term memory elements are set to play a key role by creating new representations in terms of a space-time matrix. The obtained representations are delivery as input to a second shallow network which acts as ”recognizer”. A noise balanced learning method is used to fast train the recognizer with real-world images, giving rise to a simple and yet powerful robotic eye, with a slender neural processor that vigorously tracks and recognizes the chosen object. The system has been tested with real images in real time.
Źródło:: Journal of Artificial Intelligence and Soft Computing Research; 2017, 7, 2; 125-136
2083-2567
2449-6499
Pojawia się w:: Journal of Artificial Intelligence and Soft Computing Research
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 8.

Tytuł:: Dynamic states equations of transport pipeline in deep-sea mining
Autorzy:: Sobota, Jerzy
Jianxin, Xia
Kirichenko, Evgeniy
Powiązania:: https://bibliotekanauki.pl/articles/2073867.pdf
Data publikacji:: 2021
Wydawca:: Polska Akademia Nauk. Czytelnia Czasopism PAN
Tematy:: górnictwo głębinowe
rurociąg głębinowy
rurociąg transportowy
deep-sea mining
vertical pipeline
stability of deep-sea pipeline
Opis:: The transport pipeline of lifting the underwater minerals to the surface of the water onto the ship during the movement of the vessel takes in the water a curved deformed shape. Analysis of the state of stability of the pipeline showed that if the flow velocity of fluid in the pipeline exceeds a certain critical value Vkr, then its small random deviations from the equilibrium position may develop into deviations of large amplitude. The cause of instability is the presence of the centrifugal force of the moving fluid mass, which occurs in places of curvature of the axis of the pipeline and seeks to increase this curvature when the ends of the pipeline are fixed. When the critical flow velocity is reached, the internal force factors become unable to compensate for the action of centrifugal force, as a result of that a loss of stability occurs. Equations describing this dynamic state of the pipeline are presented in the article.
Źródło:: Archives of Mining Sciences; 2021, 66, 3; 385--392
0860-7001
Pojawia się w:: Archives of Mining Sciences
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 9.

Tytuł:: INTEGRATION OF MOOC PRINCIPLES INTO A LANGUAGE COURSE FRAMEWORK FOR NATO DEEP: A CASE STUDY
Autorzy:: JÓŹWIAK, Marcin
Powiązania:: https://bibliotekanauki.pl/articles/546701.pdf
Data publikacji:: 2018
Wydawca:: Uniwersytet Warmińsko-Mazurski w Olsztynie
Tematy:: NATO,
DEEP
Opis:: The presented framework is fluid in terms of design; it can be applied to both: suit needs of a different target group and subject. However, this paper focuses solely on language learning and should be applied to provide training only in this dimension. The e-learning platform used in this project is LMS ILIAS; however, it would be possible to apply another system of this class (learning management system). Nonetheless, it is advisable to use LMS ILIAS, as it suits this project’s needs and is compliant with the NATO DEEP Portal project. Ideally, the people involved in this project should know the specifics of working with military personnel of various countries. Additionally, all the role-holders are required to have experience with e-learning project design based on the ADDIE model of instructional design. The author recommends launching the project with a pilot phase first, so the initial assumptions would be properly revised.
Źródło:: Civitas et Lex; 2018, 4(20); 7-13
2392-0300
Pojawia się w:: Civitas et Lex
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Skocz do pozycji: 10.

Tytuł:: Track finding with Deep Neural Networks
Autorzy:: Kucharczyk, Marcin
Wolter, Marcin
Powiązania:: https://bibliotekanauki.pl/articles/305791.pdf
Data publikacji:: 2019
Wydawca:: Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie. Wydawnictwo AGH
Tematy:: deep neural networks
machine learning
tracking
HEP
Opis:: High energy physics experiments require fast and efficient methods for reconstructing the tracks of charged particles. The commonly used algorithms are sequential and the required CPU power increases rapidly with the number of tracks. Neural networks can speed up the process due to their capability of modeling complex non-linear data dependencies and finding all tracks in parallel. In this paper, we describe the application of the deep neural network for reconstructing straight tracks in a toy two-dimensional model. It is planned to apply this method to the experimental data obtained by the MUonE experiment at CERN.
Źródło:: Computer Science; 2019, 20 (4); 475-491
1508-2806
2300-7036
Pojawia się w:: Computer Science
Dostawca treści:: Biblioteka Nauki

Artykuł

Zmień widok

na półce

Informacja

Wyszukujesz frazę "deep" wg kryterium: Wszystkie pola

Źródło danych

Dostawca treści

Podbaza

Kolekcja

Rok wydania

Wydawca

Temat

Autor

Typ dokumentu

Język