• Journal of the Korean Institute of Telematics and Electronics C
• /
• v.36C no.10
• /
• pp.66-74
• /
• 1999

In this paper, we propose a generalized model of statistical Hopfield neural network applicable to solving the well known NP-Complete problem, TSP. Van Den Bout's method to simplify the energy function through normalization has severe weak points that it does not consider the necessary perturbation effects. In proposed model, the improved energy function is used and 5 kinds of perturbation effects and the ratio between perturbation effects are considered including van Den Bout's 2 kinds and one more kind of Park. Through the simulation of randomly generated distribution of 10-city, it is found that our model shows 90 out of 100 cases reach the optimum and near optimum solution(within 5% error). We show the simulation of the large scale, 30-city and 50-city.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.15 no.8
• /
• pp.667-677
• /
• 1990

In this paper, optical inplementation of the Hopfield neural network model for two-dimensinal associative memory is described For the real-time processing of two-dimensional images, the commercial LCTVs are used as a memory mask and an input spatical light modulator. A 4-D memory matrix is realized with a 2-D mask of a matrix arrangement and the inner-products between arbitrary input pattern and memory matrix are carried out by using the multifocus hololens. The output image is then electronically thresholded and fed back to the input of the associative memory system by 2-D CCd camera. From the good experimental results for the high error correction capability, the proposed system can be applied to practical pattern recognition and machine vision systems.

• Proceedings of the KIEE Conference
• /
• 1990.07a
• /
• pp.532-534
• /
• 1990

We suggest a new energy function that improves the area complexity of the Hopfield Crossbar Network. Through converting data representation to an encoded format, we reduce the number of nodes of the network, and thus reduce the entire size. We apply this approach to the layer assignment problem, and use the modified delayed self-feedback Hopfield Network. Area complexity of the existing network for layer assignment ploblem is improved from O( $N^2L^2$ ) to O($N^2$(log L)$^2$).

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.16 no.6
• /
• pp.545-555
• /
• 1991

In this paper, We discuss optical implementation of new optical adaptive patern recognition system based on single layer perception with learning capability and associative memory model having error corrective capability. The single layer perceptron is optically implemented by using 2 D LCTV spatial light modulators through the nonlinear quantization and polarization encoding methods, and 2 D hopfield associative memory is also implemented by using multifocus holographic lens. From some experimental results on classfication of Arabic numbers into even & edd numbers, it is shown that the proposed system can classify the patterns to the right classes correctly even for the partial and erronenous input patterns. Accordingly, the proposed optical adaptive pattern recognition system can be suggested for practical application in the fields of image processing and pattern recognition.

• Journal of the Korea Society of Computer and Information
• /
• v.10 no.4 s.36
• /
• pp.17-27
• /
• 2005

In this study, it proposes the neural network system for character recognition and restoration. Proposes system composed by recognition part and restoration part. In the recognition part. it proposes model of effective pattern recognition to improve ART Neural Network's performance by restricting the unnecessary top-down frame generation and transition. Also the location feature extraction algorithm which applies with Hangeul's structural feature can apply the recognition. In the restoration part, it composes model of inputted image's restoration by Hopfield neural network. We make part experiments to check system's performance, respectively. As a result of experiment, we see improve of recognition rate and possibility of restoration.

• Proceedings of the KIEE Conference
• /
• 1993.07a
• /
• pp.254-257
• /
• 1993

This paper presents a new method to implement Hebbian learning method on artificial neural network. In hebbian learning algorithm, complexity in terms of multiplications is high. To save the chip area, we consider a new learning circuit. By calculating similarity, or correlation between $X_i$ and $O_i$, large portion of circuits commonly used in conventional neural networks is not necessary for this new hebbian learning circuit named COR. The output signals of COR is applied to weight storage capacitors for direct control the voltages of the capacitors. The weighted sum, ${\Sigma}W_{ij}O_j$, is realized by multipliers, whose output currents are summed up in one line which goes to learning circuit or output circuit. The drain current of the multiplier can produce positive or negative synaptic weights. The pass transistor selects eight learning mode or recall mode. The layout of an learnable six-neuron fully connected Hopfield neural network is designed, and is simulated using PSPICE. The network memorizes, and retrieves the patterns correctly under the existence of minor noises.

• Investigative Magnetic Resonance Imaging
• /
• v.6 no.2
• /
• pp.137-146
• /
• 2002

Purpose : This paper introduces an improved classification approach which adopts a deterministic relaxation method and an agglomerative clustering technique for the classification of MRI using neural network. The proposed approach can solve the problems of convergency to local optima and computational burden caused by a large number of input patterns when a neural network is used for image classification. Materials and methods : Application of Hopfield neural network has been solving various optimization problems. However, major problem of mapping an image classification problem into a neural network is that network is opt to converge to local optima and its convergency toward the global solution with a standard stochastic relaxation spends much time. Therefore, to avoid local solutions and to achieve fast convergency toward a global optimization, we adopt MFA to a Hopfield network during the classification. MFA replaces the stochastic nature of simulated annealing method with a set of deterministic update rules that act on the average value of the variable. By minimizing averages, it is possible to converge to an equilibrium state considerably faster than standard simulated annealing method. Moreover, the proposed agglomerative clustering algorithm which determines the underlying clusters of the image provides initial input values of Hopfield neural network. Results : The proposed approach which uses agglomerative clustering and deterministic relaxation approach resolves the problem of local optimization and achieves fast convergency toward a global optimization when a neural network is used for MRI classification. Conclusion : In this paper, we introduce a new paradigm to classify MRI using clustering analysis and deterministic relaxation for neural network to improve the classification results.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.33B no.6
• /
• pp.186-197
• /
• 1996

A multiple target tracking (MTT) problem is to track a number of targets in clusttered environment, where measurements may contain uncertainties of measurement origin due to clutter, missed detection, or other targets, as well as measurement noise errors. Hence, an MTT filter should be introduced to resolve this problem. In this paper, a neural network is rpoposed as an MTT filter.

• Journal of Institute of Control, Robotics and Systems
• /
• v.6 no.6
• /
• pp.447-453
• /
• 2000

Using the scattering theory of laser light, we analyze the particle sizing method. The scattered profile measured by the photodetector is sampled, scale conditioned by a 32 channel analog-to-digital converter, and is analyzed with the transform matrix from the light energy signals to the weights of the particle sizes. The particle size distribution is classified using the Hopfield neural network method as well as the conventional nonnegative least square method.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.29B no.7
• /
• pp.70-78
• /
• 1992

In this paper, an approach for 3-D object segmentation and classification, which is based on eigen-values of polynomial function as their surface features, using neural network is proposed. The range images of 3-D objects are classified into surface primitives which are homogeneous in their intrinsic eigenvalue properties. The misclassified regions due to noise effect are merged into correct regions satisfying homogeneous constraints of Hopfield neural network. The proposed method has advantage of processing both segmentation and classification simultaneously.