• Journal of Information Technology Applications and Management
• /
• v.9 no.2
• /
• pp.1-16
• /
• 2002

Recently, neural network methods have been studied to find out more valuable information in data bases. But the supervised learning methods of neural networks have an overfitting problem, which leads to errors of target patterns. And the unsupervised learning methods can distort important information in the process of regularizing data. Thus they can't efficiently classify data, To solve the problems, this paper introduces a hybrid neural networks HACAB(Hybrid Algorithm combining a Competition learning model And BP Algorithm) combining a competition learning model and 8P algorithm. HACAB is designed for cases which there is no target patterns. HACAB makes target patterns by adopting a competition learning model and classifies input patterns using the target patterns by BP algorithm. HACAB is evaluated with random input patterns and Iris data In cases of no target patterns, HACAB can classify data more effectively than BP algorithm does.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1329-1342
• /
• 2018

Recent advances in quantum computer development have raised the issue of the security of RSA and elliptic curve cryptography, which are widely used. In response, the National Institute of Standards and Technology(NIST) is working on the standardization of public key cryptosystem which is secure in the quantum computing environment. Lattice-based cryptography is a typical post-quantum cryptography(PQC), and various lattice-based cryptographic schemes have been proposed for NIST's PQC standardization contest. Among them, EMBLEM proposed a new multi-bit encryption method which is more intuitive and efficient for encryption and decryption phases than the existing LWE-based encryption schemes. In this paper, we propose a multi-bit encryption scheme with improved efficiency using LWR assumption. In addition, we prove the security of our schemes and analyze the efficiency by comparing with EMBLEM and R.EMBLEM.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.1
• /
• pp.108-113
• /
• 2022

The deep-learning-based measurement method with the through-focus scanning optical microscopy (TSOM) estimated the size of the object using the classification. However, the measurement performance of the method depends on the number of subdivided classes, and it is practically difficult to prepare data at regular intervals for training each class. We propose an approach to measure the size of an object in the TSOM image using the deep-learning regression model instead of using classification. We attempted our proposed method to estimate the top critical dimension (TCD) of through silicon via (TSV) holes with 2461 TSOM images and the results were compared with the existing method. As a result of our experiment, the average measurement error of our method was within 30 nm (1σ) which is 1/13.5 of the sampling distance of the applied microscope. Measurement errors decreased by 31% compared to the classification result. This result proves that the proposed method is more effective and practical than the classification method.

• Preventive Nutrition and Food Science
• /
• v.7 no.3
• /
• pp.265-272
• /
• 2002

In this study, we examined the effects of dietary fatty acids on the fatty acid composition of phospholipid fractions in regions of the brain and on behavioral development in rats. The Sprague Dawley rats were fed the experimental diets 3~4 wks prior to the conception. Experimental diets consisted of 10% fat(wt/wt) which were from either safflower oil (SO, poor in $\omega$3 fatty acids), mixed oil MO, P/M/S ratio : 1:1.4:1, $\omega$6/$\omega$3 ratio = 6.3), or mixed oil supplemented with vitamin E (+500 mg/kg diet). At 3 and 9 weeks of age, frontal cortex (FC), corpus striatum (CS), hippocampus (H), and cerebellum (CB) were dissected from the whole brain. The fatty acid content was determined in the different phospholipid fractions: phosphatidylcholine (PC), phosphatidyl-serine (PS), and phosphatidylethanolamine (PE) in the rat brain regions. In the visual discrimination test, the order of the cumulative errors made in Y-water maze test were SO > MO > ME. This suggested that the balanced diet supplemented with vitamin I had the most beneficial effect on learning ability. The overall characteristics of correlation between fatty acids and behavior development were that the frequency of cumulative errors were negatively correlated significantly with monounsaturated fatty acids (MUFAs), ie., 18:1 $\omega$9 and 22:1 $\omega$9. Docosa-hexaenoic acid (22:6 $\omega$3) of PS in frontal cortex (FC) was negatively correlated with the number of errors made in the Y-water maze test.22:5 $\omega$6 PS in hippocampus (H), PC and PE in corpus striatum (CS), PC in cerebellum (CB) were positively correlated with cumulative errors. And these errors were negatively correlated with 20:4 $\omega$ 6 of PE in corpus striatum (CS) and PC in cerebellum (CB). Especially, O1eic acid (18:1 u 9) in all phospholipid fractions (PC, PS, PE) of hippocampus was negatively correlated with the number of errors. These findings demonstrate that the MUFAs were might be essential for proper brain development, especially in hippocampus which is generally thought to be the regions of memory and learning.

• Journal of the Ergonomics Society of Korea
• /
• v.5 no.2
• /
• pp.11-15
• /
• 1986

In this paper, we consider the validity of a human probabilistic learning model applied to the perdiction of errors associated with the absolute identification of tones. It is shown that the probabilistic learning model describes the human error process adequately. The model parameters are estimated by two methods which are the method of maximum likelihood, and the method of mement. The MLE version of the model has the better predictive power but the ME version is more readily obtainable and may be more practical.

• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.1278-1280
• /
• 1996

In this paper, an Iterative learning control algorithm is presented for a class of non linear system which have external inputs or disturbances. The acceleration of error signal is used to update the next control signal. It is shown that the feedback gain can be deter.ined so that the overall errors are convergent.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.9
• /
• pp.159-165
• /
• 1994

In this paper, we propose a multi-layer associative neural network structure suitable for hardware implementaion with the function of performance refinement and improved robutst capability. Unlike other methods which reduce network complexity by putting restrictions on synaptic weithts, we are imposing a requirement of hidden layer neurons for the function. The proposed network has synaptic weights obtainted by Hebbian rule between adjacent layer's memory patterns such as Kosko's BAM. This network can be extended to arbitary multi-layer network trainable with Genetic algorithm for getting hidden layer memory patterns starting with initial random binary patterns. Learning is done to minimize newly defined network error. The newly defined error is composed of the errors at input, hidden, and output layers. After learning, we have bidirectional recall process for performance improvement of the network with one-shot recall. Experimental results carried out on pattern recognition problems demonstrate its performace according to the parameter which represets relative significance of the hidden layer error over the sum of input and output layer errors, show that the proposed model has much better performance than that of Kosko's bidirectional associative memory (BAM), and show the performance increment due to the bidirectionality in recall process.

• Journal of the Korean Operations Research and Management Science Society
• /
• v.33 no.3
• /
• pp.93-105
• /
• 2008

Semi-supervised learning uses a small amount of labeled data to predict labels of unlabeled data as well as to improve clustering performance, whereas unsupervised learning analyzes only unlabeled data for clustering purpose. We propose a new clustering-based semi-supervised learning method by reflecting the initial predicted labels of unlabeled data on the objective function. The initial prediction should be done in terms of a discrete probability distribution through a classification method using labeled data. As a result, clusters are formed and labels of unlabeled data are predicted according to the Information of labeled data in the same cluster. We evaluate and compare the performance of the proposed method in terms of classification errors through numerical experiments with blinded labeled data.

• Proceedings of the KIEE Conference
• /
• 1990.11a
• /
• pp.421-424
• /
• 1990

An iterative learning control scheme for exact-tracking control and parameter estimation of uncertain robotic systems is presented. In the learning control structure, tracking and feedforward input converge globally and asymptotically as iteration increases. Since convergence of parameter errors depends only on the persistent exciting condition of system trajectories along the iteration independently of length of trajectories, it may be achieved with only system trajectories of small duration. In addition, these learning control schemes are expected to be effectively applicable to time-varying parametric systems as well as time-invariant systems, for the parameter estimation is performed at each fixed time along the iteration. Finally, no usage of acceleration signal and no in version of estimated inertia matrix in the parameter estimator makes these learning control schemes more feasible.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.20 no.42
• /
• pp.161-169
• /
• 1997

A variety of learning methods are used for neural networks. Among them, the backpropagation algorithm is most widely used in such image processing, speech recognition, and pattern recognition. Despite its popularity for these application, its main problem is associated with the running time, namely, too much time is spent for the learning. This paper suggests a method which maximize the convergence speed of the learning. Such reduction in e learning time of the backpropagation algorithm is possible through an adaptive adjusting of the slope of the activation function depending on total errors, which is named as the variable slope algorithm. Moreover experimental results using this variable slope algorithm is compared against conventional backpropagation algorithm and other variations; which shows an improvement in the performance over pervious algorithms.