Wyniki wyszukiwania - BazTech

1

Application of Hybrid Neural Network System in Image Processing

Rykała Łukasz

Systemy Logistyczne Wojsk

|

2019

|

Vol. 51, no. 2

141--153

EN

The article describes the use of feedforward two-layer neural network and recursive neural network with feedback, i.e. Hopfield network within a system capable of performing associative memory functions. It has been shown that these structures can be used successfully alone, however, using them together in series in the listed above order significantly improves system performance.

2

Accuracy influence of the hardware implementation of the Hopfield network on the solution quality for the travelling salesman problem

Nagórny Z.

Journal of Applied Computer Science

|

2012

|

Vol. 20, nr 1

51-67

EN

The objective of this work was to study the accuracy influence of the hardware implementation of the Hopfield network on the solution quality for the travelling salesman problem. In this work the 8-bit accuracy influence of the hardware implementation of weights, activation functions, and external input signals on the quality of achieved solutions for 100 randomly generated instances of the 10-city TSP was studied and comparable results in comparison with the simulation in which the network was simulated using double precision floating point numbers were obtained. The results show that the hardware implementation of the Hopfield network with the 8-bit accuracy allows to obtain satisfactory solutions for the TSP. It should be also noted that the network described in this work utilizes the novel method of auto-tuning of Hopfield network parameters and thanks to this method, in contrast to other works, none of the network parameters is tuned for a given solved TSP on the basis of preliminary simulations. The Hopfield network presented in this work is destined for the hardware implementation. The application of the hardware implementation of the network could significantly decrease the time required to obtain the combinatorial problem solution in comparison with methods using von Neumann architecture computers.

3

Badanie skuteczności autoasocjacyjnej sieci Hopfielda w zagadnieniu Ogólnej Analizy Kształtu

Gościewska K.

Metody Informatyki Stosowanej

|

2011

|

nr 4

241-250

EN

The paper presents experimental results of employing Hopfield network to the problem of General Shape Analysis (GSA). This problem is similar to traditional retrieval or recognition of shapes extracted from digital images. The main difference is that GSA’s main goal is not to identify object’s shape but to define its similarity to the one or few general templates. Templates are simple shapes, such as circle, square or triangle. This approach determines the most general information about a shape. The experiment was performed using 50 various shapes, among which 10 were general templates and the rest were test objects. The task was to indicate the most similar template for each of the test objects.

4

Projektowanie topografii systemów VLSI. Cz. 4. Symulowane wyżarzanie, sieci neuronowe

Nagórny Z., Kos A.

Kwartalnik Elektroniki i Telekomunikacji

|

2006

|

Vol. 52, z. 4

697-727

PL

Niniejsza praca jest czwartą, ostatnią częścią przeglądu metod rozmieszczania modułów, stosowanych podczas projektowania topografii układów VLSI. Modułem jest fragment systemu wyodrębniony ze względu na pełnioną funkcję. Praca jest poświęcona algorytmowi symulowanego wyżarzania oraz sieciom neuronowych. Przedstawiono dokładny opis algorytmu symulowanego wyżarzania oraz sposób zastosowania algorytmu do rozmieszczania modułów. Programy wykorzystujące algorytm symulowanego wyżarzania zostały szczegółowo opisane. W tym celu scharakteryzowano następujące programy rozmieszczania: TimberWolf, MGP, MPG-MS, VPR. Następnie, opisano sposób zastosowania sieci samoorganizującej się oraz sieci Hopfielda w optymalizacji topografii układów VLSI. Przedstawiono rezultaty rozmieszczania modułów otrzymane z użyciem sieci Hopfielda. Następnie, scharakteryzowano inne metody stosowane podczas rozmieszczania modułów: algorytmy genetyczne, strategie ewolucyjne, schemat rozmieszczanie-planowanie topografii-rozmieszczanie, programy dla układów 3D VLSI oraz sprzętowe metody rozwiązania problemu rozmieszczania modułów. Porównano metody rozmieszczania modułów przedstawione w przeglądzie.

EN

The design process of the VLSI circuits requires the use of computer aided design tools. This paper is the fourth part of the survey of the cell placement techniques for digital VLSI circuits. In this part of the survey, the simulated annealing algorithm and neural networks are presented. An application of the simulated annealing algorithm to the cell placement problem is described. Nowadays the tools used for the cell placement, which utilize the presented algorithms are characterized: TimberWolfSC, TimberWolfMC, MGP, MPG-MS, VPR. Then, applications of neural networks to the cell placement problem are described. A self-organizing network and Hopfield network for the cell placement problem are presented. Some circuit layouts generated by using the Hopfield network are presented. Applications of a genetic algorithm, evolutionary strategy, three-stage placement-floorplanning-placement flow and special purpose hardware for the cell placement are described. Tools used for the 3D VLSI cell placement are characterized. Some conclusions concerning described techniques and tools are presented.

5

Rozpoznawanie obrazów obrabiarek z zastosowaniem sieci neuronowej Hopfielda

Gałuszka E., Głośny J., Sokołowski A.

Prace Naukowe Katedry Budowy Maszyn / Politechnika Śląska

|

2005

|

nr 4

167-176

PL

Celem prezentowanych badań jest przybliżenie podstawowych zagadnień związanych z sieciami neuronowymi Hopfielda oraz próby zastosowania do rozpoznawania obrazów obrabiarek. Rozpoznawanie obrazów przez sieć Hopfielda może być wykorzystane np. przy pomiarze pola temperatur i prowadzeniu analiz odkształceń termicznych obrabiarek.

EN

The paper presents some results of the research aiming at determining applicability of Hopfield artificial neural network for pattern recognition. In our research, the Hopfield neural network was tested for digital image correction. In order to perform the tests, four digital images were generated. The tests revealed that the network correctly recognized (corrected) all noisy patterns.

6

Porównanie działania sieci Hopfielda i algorytmów genetycznych dla problemu komiwojażera

Klimek M., Grabska-Chrząstowska J.

Automatyka / Akademia Górniczo-Hutnicza im. Stanisława Staszica w Krakowie

|

2004

|

T. 8, z. 3

459-467

PL

W artykule zostały przedstawione wyniki zastosowania sieci typu Hopfielda do rozwiązywania problemu komiwojażera, standardowego problemu testowego dla różnych narzędzi optymalizacyjnych. W celu porównania efektywności działania zaimplementowanej sieci dodano algorytm genetyczny rozwiązujący problem komiwojażera i porównano wyniki osiągane przez poszczególne algorytmy. Prosty algorytm genetyczny okazał się nieporównanie lepszy od najlepiej skonfigurowanej sieci Hopfielda.

EN

The paper presents the results of using Hopfield type neural networks to solve the Travelling Salesman Problem, a standard test problem for various optimisation tools. A genetic algorithm solving the TSP was added in order to compare the efficiency of the implemented network functioning and the results obtained by particular algorithms were compared. The simple genetic algorithm appeared incomparably better than the best configured Hopfield network.

7

Neural networks for the N-Queens Problem : a review

Mańdziuk J.

Control and Cybernetics

|

2002

|

Vol. 31, no 2

217-248

EN

Neural networks can be successfully applied to solving certain types of combinatorial optimization problems. In this paper several neural approaches to solving constrained optimization problems are presented and their properties discussed. The main goal of the paper is to present various improvements to the wellknown Hopfield models which are intensively used in combinatorial optimization domain. These improvements include deterministic modifications (binary Hopfield model with negative self-feedback connections and Maximum Neural Network model), stochastic modifications (Gaussian Machine), chaotic Hopfield-based models (Chaotic Neural Network and Transiently Chaotic Neural Network), hybrid approaches (Dual-mode Dynamic Neural Network and Harmony Theory approach) and finally modifications motivated by digital implementation feasibility (Strictly Digital Neural Network). All these models are compared based on a commonly used benchmark prohlem - the N-Queens Problem (NQP). Numerical results indicate that each of modified Hopfield models can be effectively used to solving the NQP. Coonvergence to solutions rate of these methods is very high - usually close to 100%. Experimental time requirements are generally low - polynomial in most casos. Some discussion of non-neural, heuristic approaches to solving the NQP is also presented in the paper.