A new synthesis approach for feedback neural networks based on the perceptron training algorithm

Liu, D.; Lu, Zanjun

doi:10.1109/72.641469

Cited by 68 publications

(53 citation statements)

References 31 publications

(105 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…These patterns were the desired output of the network and the entries for training are the same patterns with a Gaussian noise of 20%. [17] reproduced and compared five different training algorithms for CNNs, among them a method based on perceptrons was developed by [18] The weights W i of (5) are found by the algorithm of perceptron training [15]. The objective of the training of a CNN is to obtain T and B using the perceptron training algorithm and evaluate the stability of x in (2).…”

Section: Cellular Neural Networkmentioning

confidence: 99%

Position Estimation Of UAV By Image Processing With Neural Networks

Goltz¹,

Shiguemori²,

Velho³

2016

Anais Do 10. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

-This paper presents a study of three artificial neural networks with supervised training and different architectures: network with radial basis function, multilayer perceptron and cellular neural network. These networks were applied to edge detection in aerial and satellite images, for later correlation calculation in spatial domain between these images to simulate the estimation of the geographical position of a unmanned aerial vehicle -UAV. The neural networks results were compared with Sobel and Canny operators.Keywords -Artificial Neural Networks, Image Processing and Air Navigation by Images. IntroductionThe application of UAV stepped up lately due to low operational and manufacture costs compared to conventional aircrafts, don't have crew, among other factors. UAVs are employed in remote sensing, with synthetic aperture radar (SAR) or optical sensors on board, for monitoring cities, human activities or areas of risk such as conflict zones or natural disasters. Radio controlled UAVs usually use antennas with linited reach. In addition, when flying they are subject to possible interferences in the communication process with the control base. Interference in the signal can also occur with UAVs use Global Positioning System (GPS) signals combined with the INS (Inertial Navigation System) for navigation. Possible blocking of GPS signals may also become a limitation to its use. An alternative to overcome these problems is to make use of air navigation systems based real time captured ground information.The use of image processing, computer vision, geoprocessing, and pattern recognition techniques applied to autonomous navigation of UAVs is seen in some studies as in [1], using digital elevation model, in [2] using edge information for the registration of aerial images from satellite image, stereo vision in [3], matching between images in [4], among many.Many papers use ANNs in the navigation system of UAVs, research by [5] shows it. In the literature there are few studies using ANNs in image processing and / or pattern recognition in images in order to help the navigation of UAVs. But the use of ANNs for this purpose can be seen in some studies as in [6], that developed an ANN classify surface in candidate regions for crash in the landing phase of a UAV after the segmentation of the terrain flown. The landing area is chosen using fuzzy rules that use data of the terrain available in the database of the covered areas. The work of [7] also developed an aplication in which ANNs are used in the processing of captured images of the area flown by the UAV. Initially, the texture of the image is extracted by a Gabor filter and an ANN searches the area between some landmarks used for navigation of the UAV, derived from a satellite image. An MLP and a self-organizing map of Kohonen -SOM -were developed for this purpose and their results were compared.

show abstract

Section: Cellular Neural Networkmentioning

confidence: 99%

Position Estimation Of UAV By Image Processing With Neural Networks

Goltz¹,

Shiguemori²,

Velho³

2016

Anais Do 10. Congresso Brasileiro De Inteligência Computacional

View full text Add to dashboard Cite

show abstract

“…The properties of equilibrium points of neural systems play an important role in some practical problems, such as optimization solvers (Chen, 2000;Forti, 1995;Kennedy, 1988;Tank and Hopfield, 1986;Sudharsanan and Sundareshan, 1991), pattern recognition (Liu and Lu, 1997) and image compression (Venetianer and Roska, 1998). It is well known that an equilibrium point can be viewed as a special periodic solution of continuous-time neural systems with arbitrary period (Zhang, 2002;Feng, 2003, 2004;).…”

Section: Introductionmentioning

confidence: 99%

On Robust Exponential Stability of a Class of Attractor Neural Networks

Sun

Shi

2005

IFAC Proceedings Volumes

View full text Add to dashboard Cite

Robust Exponential stability of continuous-time attractor neural networks with delays is discussed. A new sufficient condition ensuring existence and uniqueness of periodic solution for a general class of interval dynamical systems are obtained. Discretetime analogue of the continuous-time systems with periodic input is formulated and we study their dynamical characteristics. The robust exponential stability and periodicity of the continuous-time systems is preserved by the discrete-time analogue without any restriction imposed on the uniform discretization step-size.

show abstract

“…Não se pode provar, portanto, que soluções periódicas ou caóticas não existirão na dinâmica resultante do sistema. Em [Liu & Lu, 1997], por exemplo,é proposta uma modificação do algoritmo de treinamento baseado em Perceptrons, que leva em consideração essa preocupação quanto a estabilidade da rede. No artigo,é apresentado um algoritmo que resulta em uma matriz T simétrica, garantindo, portanto, que apenas pontos de equilíbrios exis-tam na dinâmica da rede.…”

Section: Discussionunclassified

“…O método apresentado nesta seção, proposto por Liu e Lu [Liu & Lu, 1997], se utiliza de um Perceptron [Rosenblatt, 1958] para encontrar a matriz de conexões da rede. Na Seção 6.5.1, o conceito de Perceptroné revisto e na Seção 6.5.2, a estratégia de solução que utiliza este conceitoé apresentada.…”

A new synthesis approach for feedback neural networks based on the perceptron training algorithm

Cited by 68 publications

References 31 publications

Position Estimation Of UAV By Image Processing With Neural Networks

Position Estimation Of UAV By Image Processing With Neural Networks

On Robust Exponential Stability of a Class of Attractor Neural Networks

Memória associativa em redes neurais realimentadas

Contact Info

Product

Resources

About