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 "Neural Networks" wg kryterium: Temat

  Lista filtrów
Wyrównaj
Wyświetlanie 1-15 z 48
Tytuł:
Neural Network-Based Narx Models in Non-Linear Adaptive Control
Autorzy:
Dzieliński, A.
Powiązania:
https://bibliotekanauki.pl/articles/907986.pdf
Data publikacji:
2002
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
automatyka
neural networks
adaptive control
nonlinear systems
Opis:
The applicability of approximate NARX models of non-linear dynamic systems is discussed. The models are obtained by a new version of Fourier analysis-based neural network also described in the paper. This constitutes a reformulation of a known method in a recursive manner, i.e. adapted to account for incoming data on-line. The method allows us to obtain an approximate model of the non-linear system. The estimation of the influence of the modelling error on the discrepancy between the model and real system outputs is given. Possible applications of this approach to the design of BIBO stable closed-loop control are proposed.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2002, 12, 2; 235-240
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Evolving co-adapted subcomponents in assembler encoding
Autorzy:
Praczyk, T.
Powiązania:
https://bibliotekanauki.pl/articles/929831.pdf
Data publikacji:
2007
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
sieci neuronowe
ewolucja
neuroewolucja
neural networks
evolution
neuroevolution
Opis:
The paper presents a new Artificial Neural Network (ANN) encoding method called Assembler Encoding (AE). It assumes that the ANN is encoded in the form of a program (Assembler Encoding Program, AEP) of a linear organization and of a structure similar to the structure of a simple assembler program. The task of the AEP is to create a Connectivity Matrix (CM) which can be transformed into the ANN of any architecture. To create AEPs, and in consequence ANNs, genetic algorithms (GAs) are used. In addition to the outline of AE, the paper also presents a new AEP encoding method, i.e., the method used to represent the AEP in the form of a chromosome or a set of chromosomes. The proposed method assumes the evolution of individual components of AEPs, i.e., operations and data, in separate populations. To test the method, experiments in two areas were carried out, i.e., in optimization and in a predator-prey problem. In the first case, the task of AE was to create matrices which constituted a solution to the optimization problem. In the second case, AE was responsible for constructing neural controllers used to control artificial predators whose task was to capture a fast-moving prey.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2007, 17, 4; 549-563
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
On solving selected problems of linear algebra by means of neural networks
Zagadnienie rozwiązywania wybranych zadań algebry liniowej za pomocą sieci neuronowych
Autorzy:
Mrówczyńska, M.
Powiązania:
https://bibliotekanauki.pl/articles/395896.pdf
Data publikacji:
2011
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
sieci neuronowe
algebra liniowa
neural networks
linear algebra
linear systems
Opis:
The paper presents selected practical applications and results of computer simulations from the field of numerical linear algebra realized by means of neural networks. Bearing in mind aspects of applications, it has been decided that priority should be given to the description of the problem of soling over-determined linear systems in the norm l_2 and the norm l_1.
W pracy przedstawiono wybrane zastosowania praktyczne i wyniki symulacji komputerowych z zakresu numerycznej algebry liniowej, realizowanej za pomocą sieci neuronowych. Mając na względzie aspekty zastosowań, uznano za celowe nadać priorytet opisowi zagadnienia wyrównania nadokreślonych układów liniowych w normie l_2 oraz w normie l_1. Do standardowych operacji numerycznych zaliczono również algorytmy obliczania inwersji macierzy kwadratowych oraz wyznaczania ich wartości własnych i wektorów własnych.
Źródło:
Civil and Environmental Engineering Reports; 2011, 7; 5-17
2080-5187
2450-8594
Pojawia się w:
Civil and Environmental Engineering Reports
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Classification, Association and Pattern Completion Using Neural Similarity Based Methods
Autorzy:
Duch, W.
Adamczak, R.
Diercksen, G. H. F.
Powiązania:
https://bibliotekanauki.pl/articles/911147.pdf
Data publikacji:
2000
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
sieć neuronowa
klasyfikacja
rozpoznawanie obrazów
neural networks
classification
association
pattern recognition
Opis:
A framework for Similarity-Based Methods (SBMs) includes many classification models as special cases: neural networks of the Radial Basis Function type, Feature Space Mapping neurofuzzy networks based on separable transfer functions, Learning Vector Quantization, variants of the k nearest neighbor methods and several new models that may be presented in a network form. Multilayer Perceptrons (MLPs) use scalar products to compute a weighted activation of neurons, combining soft hyperplanes to provide decision borders. Distance-based multilayer perceptrons (D-MLPs) evaluate the similarity of inputs to weights offering a natural generalization of standard MLPs. A cluster- based initialization procedure determining the architecture and values of all adaptive parameters is described. Networks implementing SBM methods are useful not only for classification and approximation, but also as associative memories, in problems requiring pattern completion, offering an efficient way to deal with missing values. Non-Euclidean distance functions may also be introduced by normalization of the input vectors in an extended feature space. Both the approaches dramatically influence the shapes of decision borders. An illustrative example showing these changes is provided.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2000, 10, 4; 747-766
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Fuzzy and Neural Control of an Induction Motor
Autorzy:
Denai, M., A.
Attia, S. A.
Powiązania:
https://bibliotekanauki.pl/articles/908003.pdf
Data publikacji:
2002
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
automatyka
fuzzy control
neural networks
induction motor
vector control
speed observer
Opis:
This paper presents some design approaches to hybrid control systems combining conventional control techniques with fuzzy logic and neural networks. Such a mixed implementation leads to a more effective control design with improved system performance and robustness. While conventional control allows different design objectives such as steady state and transient characteristics of the closed loop system to be specified, fuzzy logic and neural networks are integrated to overcome the problems with uncertainties in the plant parameters and structure encountered in the classical model-based design. Induction motors are characterised by complex, highly non-linear and time-varying dynamics and inaccessibility of some states and outputs for measurements, and hence can be considered as a challenging engineering problem. The advent of vector control techniques has partially solved induction motor control problems, because they are sensitive to drive parameter variations and performance may deteriorate if conventional controllers are used. Fuzzy logic and neural network-based controllers are considered as potential candidates for such an application. Three control approaches are developed and applied to adjust the speed of the drive system. The first control design combines the variable structure theory with the fuzzy logic concept. In the second approach neural networks are used in an internal model control structure. Finally, a fuzzy state feedback controller is developed based on the pole placement technique. A simulation study of these methods is presented. The effectiveness of these controllers is demonstrated for different operating conditions of the drive system.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2002, 12, 2; 221-233
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Improving the Generalization Ability of Neuro-Fuzzy Systems by e-Insensitive Learning
Autorzy:
Łęski, J.
Powiązania:
https://bibliotekanauki.pl/articles/908037.pdf
Data publikacji:
2002
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
informatyka
fuzzy systems
neural networks
tolerant learning
generalization control
robust methods
Opis:
A new learning method tolerant of imprecision is introduced and used in neuro-fuzzy modelling. The proposed method makes it possible to dispose of an intrinsic inconsistency of neuro-fuzzy modelling, where zero-tolerance learning is used to obtain a fuzzy model tolerant of imprecision. This new method can be called e-insensitive learning, where, in order to fit the fuzzy model to real data, the e-insensitive loss function is used. e-insensitive learning leads to a model with minimal Vapnik-Chervonenkis dimension, which results in an improved generalization ability of this system. Another advantage of the proposed method is its robustness against outliers. This paper introduces two approaches to solving e-insensitive learning problem. The first approach leads to a quadratic programming problem with bound constraints and one linear equality constraint. The second approach leads to a problem of solving a system of linear inequalities. Two computationally efficient numerical methods for e-insensitive learning are proposed. Finally, examples are given to demonstrate the validity of the introduced methods.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2002, 12, 3; 437-447
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Cmac and Its Extensions for Efficient System Modelling
Autorzy:
Szabo, T.
Horvath, G.
Powiązania:
https://bibliotekanauki.pl/articles/908287.pdf
Data publikacji:
1999
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
sieć neuronowa
implementacja sprzętowa
budowle hydrotechniczne
CMAC
neural networks
hardware implementation
Opis:
This paper deals with the family of CMAC neural networks. The most important properties of this family are the extremely fast learning capability and a special architecture that makes effective digital hardware implementation possible. The paper gives an overview of the classical binary CMAC, shows the limitations of its modelling capability, gives a critical survey of its different extensions and suggests two further modifications. The aim of these modifications is to improve the modelling capability while maintaining the possibility of an effective realization. The basic element of the first suggested hardware structure is a new matrix-vector multiplier which is based on a canonical signed digit (CSD) number representation and a distributed arithmetic. In the other version, a hierarchical network structure and a special sequential training method are proposed which can constitute a trade-off between the approximation error and generalization. The proposed versions (among them a dynamic extension of the originally static CMAC) are suitable for embedded applications where the low cost and relatively high speed operation are the most important requirements.
Źródło:
International Journal of Applied Mathematics and Computer Science; 1999, 9, 3; 571-598
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
GPS-RTK signal analysis conception in application to monitoring of engineering structures
Koncepcja analizy sygnałów GPS-RTK w zastosowaniu do monitoringu obiektów inżynierskich
Autorzy:
Gil, J.
Powiązania:
https://bibliotekanauki.pl/articles/396436.pdf
Data publikacji:
2005
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
GPS
analiza sygnałów
monitorowanie obiektów inżynierskich
signal analysis GPS-RTK
neural networks
Opis:
The paper presents a concept for analysis of GPS-RTK (Real Time Kinematic) observations in the aspect of monitoring engineering objects, exposed to deformation. It describes the on-line adaptation algorithm for the blind separation of two statistically independent signals, representing changes of the modules of "zero" vector. In order to isolate particular oscillations (trend, periodicity) from the signals observed, the exponential equalization of signals was carried out by means of the algorithm of exponential average weights, then the counter-propagation algorithm was used, which, as a vector classifier, eliminated rudimentary noise and disturbances. On that basis it was estimated that GPS signals are inharmonious cyclic signals whose basic harmonious components estimated determine the fundamental changes of the modules of the "zero" vectors.
W pracy przedstawiono koncepcję analizy obserwacji GPS-RTK (Real Time Kinematic) w aspekcie monitorowania obiektów inżynierskich, narażonych na deformacje. Opisano, działający w trybie on-line algorytm adaptacyjny ślepej separacji dwóch statystycznie niezależnych sygnałów, reprezentujących zmiany modułów wektorów "zerowych". W celu wyodrębnienia poszczególnych wahań (trendu, okresowości) z obserwowanych sygnałów, dokonano wyrównania wykładniczego sygnałów za pomocą algorytmu wykładniczych średnich ważonych, po czym zastosowano algorytm kontrpropagacji, który działając jako klasyfikator wektorowy eliminował szczątkowe szumy i zniekształcenia. Na tej podstawie ustalono, że sygnały GPS są sygnałami okresowymi nieharmonicznymi, których estymowane podstawowe składowe harmoniczne określają zasadnicze zmiany modułów wektorów "zerowych".
Źródło:
Civil and Environmental Engineering Reports; 2005, 1; 61-73
2080-5187
2450-8594
Pojawia się w:
Civil and Environmental Engineering Reports
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Stochastic Neural Networks for Feasibility Checking
Autorzy:
Strausz, G.
Powiązania:
https://bibliotekanauki.pl/articles/908272.pdf
Data publikacji:
1999
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
optymalizacja
sieć neuronowa
aproksymacja
optimization
neural networks
simulated annealing
mean-field approximation
Opis:
Complex diagnosis problems, defined by high-level models, often lead to constraint-based discrete optimization tasks. A logical description of large, complex systems usually contains numerous variables. The first test of the logical description is typically to check the feasibility in order to know that there is no contradiction in the model. This can be formulated as an optimization problem and methods of discrete optimization theory can then be used. The purpose of the paper is to show that stochastic neural networks can be applied to this type of tasks and the networks are efficient tools for finding feasible or good-quality configurations. Boltzmann and mean-field neural networks were tested on large-sized complex problems.The paper presents simulation results obtained from a real application task and compares the performance of the neural networks being examined.
Źródło:
International Journal of Applied Mathematics and Computer Science; 1999, 9, 4; 921-937
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Towards robustness in neural network based fault diagnosis
Autorzy:
Patan, K.
Witczak, M.
Korbicz, J.
Powiązania:
https://bibliotekanauki.pl/articles/929913.pdf
Data publikacji:
2008
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
diagnostyka uszkodzeń
odporność
sieć neuronowa dynamiczna
fault diagnosis
robustness
dynamic neural networks
GMDH neural network
Opis:
Challenging design problems arise regularly in modern fault diagnosis systems. Unfortunately, classical analytical techniques often cannot provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as neural networks become more and more popular in industrial applications of fault diagnosis. Taking into account the two crucial aspects, i.e., the nonlinear behaviour of the system being diagnosed as well as the robustness of a fault diagnosis scheme with respect to modelling uncertainty, two different neural network based schemes are described and carefully discussed. The final part of the paper presents an illustrative example regarding the modelling and fault diagnosis of a DC motor, which shows the performance of the proposed strategy.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2008, 18, 4; 443-454
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Abstraction Based Connectionist Analogy Processor
Autorzy:
Yasui, A.
Powiązania:
https://bibliotekanauki.pl/articles/911152.pdf
Data publikacji:
2000
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
sieć neuronowa
wiązanie dynamiczne
abstrakcja
analogy
neural networks
network pruning
dynamic binding
abstraction
Opis:
The Abstraction Based Connectionist Analogy Processor (AB-CAP) is a trainable neural network for analogical learning/inference. An internal abstraction model, which extracts the underlying relational isomorphism and expresses predicate-argument bindings at the abstract level, is induced structurally as a result of the backpropagation training coupled with a structure- pruning mechanism. AB-CAP also develops dynamically abstraction and de- abstraction mappings for the role-filler matching. Thus, the propositions including both known and inferred ones can be expressed by, induced as, stored in and retrieved from the internal structural patterns. As such, there is no need for AB-CAP to use rule-based symbolic processing such as hypothesis making and constraint satisfaction or pattern completion checking. In this paper, AB-CAP is evaluated by using some examples. In particular, incremental analogical learning by AB-CAP shows that the internal abstraction model acquired from previous analogical learning acts as a potent attracter to bind a new set of isomorphic data, manifesting the analogical memory access/retrieval characteristics of AB-CAP.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2000, 10, 4; 791-812
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Modeling and optimization of cutting parameters when turning EN-AW-1350 aluminum alloy
Autorzy:
Khrouf, F.
Tebassi, H.
Yallese, M. A.
Chaoui, K.
Haddad, A.
Powiązania:
https://bibliotekanauki.pl/articles/2174201.pdf
Data publikacji:
2022
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
sztuczna sieć neuronowa
optymalizacja
ANOVA
artificial neural networks
chip shape
optimization
response surface methodology
Opis:
An experimental investigation is carried out to examine the effects of various cutting parameters on the response criteria when turning EN-AW-1350 aluminum alloy under dry cutting conditions. The experiments related to the analysis of the influence of turning parameters on the surface roughness (Ra) and material removal rate (MRR) were carried out according to the Taguchi L27 orthogonal array (313) approach. The analysis of variance (ANOVA) was applied to characterizing the main elements affecting response parameters. Finally, the desirability function (DP) was applied for a bi-objective optimization of the machining parameters with the objective of achieving a better surface finish (Ra) and a higher productivity (MRR). The results showed that the cutting speed is the most dominant factor affecting Ra followed by the feed rate and the depth of cut. Moreover, the Artificial Neural Network (ANN) approach is found to be more reliable and accurate than its Response Surface methodology (RSM) counterpart in terms of predicting and detecting the non-linearity of the surface roughness and material removal rate mathematical models. ANN provided prediction models with a precision benefit of 8.21% more than those determined by RSM. The latter is easier to use, and provides more information than ANN in terms of the impacts and contributions of the model terms.
Źródło:
International Journal of Applied Mechanics and Engineering; 2022, 27, 2; 124--142
1734-4492
2353-9003
Pojawia się w:
International Journal of Applied Mechanics and Engineering
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
A new approach to image reconstruction from projections using a recurrent neural network
Autorzy:
Cierniak, R.
Powiązania:
https://bibliotekanauki.pl/articles/907945.pdf
Data publikacji:
2008
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
rekonstrukcja obrazu
sieć neuronowa
sieć rekurencyjna
image reconstruction from projections
neural networks
recurrent net
Opis:
A new neural network approach to image reconstruction from projections considering the parallel geometry of the scanner is presented. To solve this key problem in computed tomography, a special recurrent neural network is proposed. The reconstruction process is performed during the minimization of the energy function in this network. The performed computer simulations show that the neural network reconstruction algorithm designed to work in this way outperforms conventional methods in the obtained image quality.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2008, 18, 2; 147-157
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Convergence Analysis for Principal Component Flows
Autorzy:
Yoshizawa, S.
Helmke, U.
Starkov, K.
Powiązania:
https://bibliotekanauki.pl/articles/908317.pdf
Data publikacji:
2001
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
badanie zbieżności
sieć neuronowa
principal component analysis
neural networks
gradient flows
phase portrait
Hessians
Opis:
A common framework for analyzing the global convergence of several flows for principal component analysis is developed. It is shown that flows proposed by Brockett, Oja, Xu and others are all gradient flows and the global convergence of these flows to single equilibrium points is established. The signature of the Hessian at each critical point is determined.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2001, 11, 1; 223-236
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Tytuł:
Advances in model-based fault diagnosis with evolutionary algorithms and neural networks
Autorzy:
Witczak, M.
Powiązania:
https://bibliotekanauki.pl/articles/908460.pdf
Data publikacji:
2006
Wydawca:
Uniwersytet Zielonogórski. Oficyna Wydawnicza
Tematy:
diagnostyka uszkodzeń
algorytmy ewolucyjne
sieci neuronowe
odporność
fault diagnosis
evolutionary algorithms
neural networks
robustness
Opis:
Challenging design problems arise regularly in modern fault diagnosis systems. Unfortunately, the classical analytical techniques often cannot provide acceptable solutions to such difficult tasks. This explains why soft computing techniques such as evolutionary algorithms and neural networks become more and more popular in industrial applications of fault diagnosis. The main objective of this paper is to present recent developments regarding the application of evolutionary algorithms and neural networks to fault diagnosis. In particular, a brief introduction to these computational intelligence paradigms is presented, and then a review of their fault detection and isolation applications is performed. Close attention is paid to techniques that integrate the classical and soft computing methods. A selected group of them is carefully described in the paper. The performance of the presented approaches is illustrated with the use of the DAMADICS fault detection benchmark that deals with a valve actuator.
Źródło:
International Journal of Applied Mathematics and Computer Science; 2006, 16, 1; 85-99
1641-876X
2083-8492
Pojawia się w:
International Journal of Applied Mathematics and Computer Science
Dostawca treści:
Biblioteka Nauki
Artykuł
Wyświetlanie 1-15 z 48

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