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 "differential networks" wg kryterium: Temat

  Lista filtrów
Wyrównaj
    Wyświetlanie 1-6 z 6
    Tytuł:
    Noise Characterization of Differential Multi-Element Multiport Networks : the Wave Approach
    Autorzy:
    Dobrowolski, J. A.
    Powiązania:
    https://bibliotekanauki.pl/articles/226146.pdf
    Data publikacji:
    2015
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    differential networks
    differential noise figure
    noise waves
    noise correlation matrix
    Opis:
    In this paper there is presented and discussed a general analysis method for noise characterization of noisy multi-element multiport differential networks. It is based on mixed mode, differential and common mode, noise waves representation of noise, generalized mixed-mode scattering parameters and generalized mixed-mode noise wave correlation parameters for the network. There are derived analytical relation between the noise figure for a given output port and the noise matrix and the scattering parameters of the network, as well as the correlations between the input port noise waves. The signal to noise ratio degradation factor is derived and discussed, too. Presented results can be implemented directly in a CAD software for noise analysis of differential microwave multi-element multiport networks with differential as well as with conventional single ended ports.
    Źródło:
    International Journal of Electronics and Telecommunications; 2015, 61, 4; 395-401
    2300-1933
    Pojawia się w:
    International Journal of Electronics and Telecommunications
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Noise Analysis of Differential Multiport Networks : the Wave Approach
    Autorzy:
    Dobrowolski, J. A.
    Powiązania:
    https://bibliotekanauki.pl/articles/226027.pdf
    Data publikacji:
    2014
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    differential networks
    noise analysis
    noise waves
    noise correlation matrix
    differential noise figure
    Opis:
    In this paper there is presented and discussed a general analysis method for noise characterization of noisy multiport differential networks. It is based on mixed mode, differential and common mode, noise waves representation of noise, generalized mixed-mode scattering parameters and generalized mixed-mode noise wave correlation parameters for the network. There are derived analytical relation between the noise figure for a given output port and the noise matrix and the scattering parameters of the network, as well as the correlations between the input port noise waves. The signal to noise ratio degradation factor is derived and discussed, too. Presented results can be implemented directly in a CAD software noise analysis of differential microwave multiport networks with differential as well as with conventional single ended ports.
    Źródło:
    International Journal of Electronics and Telecommunications; 2014, 60, 4; 281-286
    2300-1933
    Pojawia się w:
    International Journal of Electronics and Telecommunications
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Training neural networks with a hybrid differential evolution algorithm
    Uczenie sieci neuronowych hybrydowym algorytmem opartym na differential evolution
    Autorzy:
    Bandurski, K.
    Kwedlo, W.
    Powiązania:
    https://bibliotekanauki.pl/articles/341051.pdf
    Data publikacji:
    2009
    Wydawca:
    Politechnika Białostocka. Oficyna Wydawnicza Politechniki Białostockiej
    Tematy:
    sieci neuronowe
    differential evolution
    gradienty sprzężone
    minima lokalne
    neural networks
    conjugate gradients
    local minima
    Opis:
    A new hybrid method for feed forward neural network training, which combines differential evolution algorithm with a gradient-based approach is proposed. In the method, after each generation of differential evolution, a number of iterations of the conjugate gradient optimization algorithm is applied to each new solution created by the mutation and crossover operators. The experimental results show, that in comparison to the standard differential evolution the hybrid algorithm converges faster. Although this convergence is slower than that of classical gradient based methods, the hybrid algorithm has significantly better capability of avoiding local optima.
    W artykule przedstawiono nową, hybrydową metodę uczenia sieci neuronowych, łączącą w sobie algorytm Differential Evolution z podejściem gradientowym. W nowej metodzie po każdej generacji algorytmu Differential Evolution, każde nowe rozwiązanie, powstałe w wyniu działania operatorów krzyżowania i mutacji, poddawane jest kilku iteracjom algorytmu optymalizacji wykorzystującego metodę gradientów sprzężonych.Wyniki eksperymentów wskazują, że nowy, hybrydowy algorytm ma szybszą zbieżność niż standardowy algorytm Differential Evolution. Mimo, iż zbieżność ta jest wolniejsza, niż w przypadku klasycznych metod gradientowych, algorytm hybrydowy potrafi znacznie lepiej unikać minimów lokalnych.
    Źródło:
    Zeszyty Naukowe Politechniki Białostockiej. Informatyka; 2009, 4; 5-17
    1644-0331
    Pojawia się w:
    Zeszyty Naukowe Politechniki Białostockiej. Informatyka
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    The training of multiplicative neuron model based artificial neural networks with differential evolution algorithm for forecasting
    Autorzy:
    Bas, E.
    Powiązania:
    https://bibliotekanauki.pl/articles/91575.pdf
    Data publikacji:
    2016
    Wydawca:
    Społeczna Akademia Nauk w Łodzi. Polskie Towarzystwo Sieci Neuronowych
    Tematy:
    artificial neural networks
    multiplicative neuron model
    differential evolution
    algorithm
    forecasting
    sztuczne sieci neuronowe
    algorytm
    prognozowanie
    Opis:
    In recent years, artificial neural networks have been commonly used for time series forecasting by researchers from various fields. There are some types of artificial neural networks and feed forward artificial neural networks model is one of them. Although feed forward artificial neural networks gives successful forecasting results they have a basic problem. This problem is architecture selection problem. In order to eliminate this problem, Yadav et al. (2007) proposed multiplicative neuron model artificial neural network. In this study, differential evolution algorithm is proposed for the training of multiplicative neuron model for forecasting. The proposed method is applied to two well-known different real world time series data.
    Źródło:
    Journal of Artificial Intelligence and Soft Computing Research; 2016, 6, 1; 5-11
    2083-2567
    2449-6499
    Pojawia się w:
    Journal of Artificial Intelligence and Soft Computing Research
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Nonstationary analysis of a queueing network with positive and negative messages
    Autorzy:
    Matalytski, M.
    Naumenko, V.
    Powiązania:
    https://bibliotekanauki.pl/articles/122613.pdf
    Data publikacji:
    2013
    Wydawca:
    Politechnika Częstochowska. Wydawnictwo Politechniki Częstochowskiej
    Tematy:
    information systems
    telecommunications systems
    information networks
    telecommunications networks
    virus
    open G-network with negative messages
    transient behavior
    system of difference-differential equations
    probability states
    generating function
    Opis:
    This paper contains an investigation of an open queueing network with positive and negative messages that can be used to model the behavior of viruses in information and telecommunication systems and networks. The purpose of research is investigation of such a network at the transient behavior. We consider the case when the intensity of the incoming flow of positive and negative messages and service intensity of messages do not depend on time. It is assumed that all queueing systems of network are one-line. We obtained a system difference-differential equations for the state probabilities of the network. To find the state probabilities of the network in the transitional behavior applied a methodology based on the use of the apparatus of multidimensional generating functions. We obtained an expression for generating function. An example is calculated.
    Źródło:
    Journal of Applied Mathematics and Computational Mechanics; 2013, 12, 2; 61-71
    2299-9965
    Pojawia się w:
    Journal of Applied Mathematics and Computational Mechanics
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
    Tytuł:
    Physics-guided neural networks (PGNNs) to solve differential equations for spatial analysis
    Autorzy:
    Borzyszkowski, Bartłomiej
    Damaszke, Karol
    Romankiewicz, Jakub
    Świniarski, Marcin
    Moszyński, Marek
    Powiązania:
    https://bibliotekanauki.pl/articles/2086847.pdf
    Data publikacji:
    2021
    Wydawca:
    Polska Akademia Nauk. Czytelnia Czasopism PAN
    Tematy:
    physics-guided neural networks
    spatial analysis
    differential equations
    machine learning
    sieci neuronowe
    fizyka
    analiza przestrzenna
    równania różniczkowe
    uczenie maszynowe
    Opis:
    Numerous examples of physically unjustified neural networks, despite satisfactory performance, generate contradictions with logic and lead to many inaccuracies in the final applications. One of the methods to justify the typical black-box model already at the training stage involves extending its cost function by a relationship directly inspired by the physical formula. This publication explains the concept of Physics-guided neural networks (PGNN), makes an overview of already proposed solutions in the field and describes possibilities of implementing physics-based loss functions for spatial analysis. Our approach shows that the model predictions are not only optimal but also scientifically consistent with domain specific equations. Furthermore, we present two applications of PGNNs and illustrate their advantages in theory by solving Poisson’s and Burger’s partial differential equations. The proposed formulas describe various real-world processes and have numerous applications in the area of applied mathematics. Eventually, the usage of scientific knowledge contained in the tailored cost functions shows that our methods guarantee physics-consistent results as well as better generalizability of the model compared to classical, artificial neural networks.
    Źródło:
    Bulletin of the Polish Academy of Sciences. Technical Sciences; 2021, 69, 6; e139391, 1--10
    0239-7528
    Pojawia się w:
    Bulletin of the Polish Academy of Sciences. Technical Sciences
    Dostawca treści:
    Biblioteka Nauki
    Artykuł
      Wyświetlanie 1-6 z 6

      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