• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1996년도 한국자동제어학술회의논문집(국내학술편); 포항공과대학교, 포항; 24-26 Oct. 1996
• /
• pp.1173-1176
• /
• 1996

Multilayer feedforward networks may be applied to identify the deterministic relationship between input and output data. When the results from the network require a high level of assurance, considering of the stochastic relationship between the data may be very important. The variance is one of the useful parameters to represent the stochastic relationship. This paper presents a new algorithm for a multilayer feedforward network to learn the variance of dispersed data without preliminary calculation of variance. In this paper, the network with this learning algorithm is named as a variance learning neural network(VALEAN). Computer simulation examples are utilized for the demonstration and the evaluation of VALEAN.

• 한국정밀공학회지
• /
• 제14권6호
• /
• pp.121-127
• /
• 1997

Multilayer feedforward networks may be applied to identify the deterministic relationship between input and output data. When the results from the network require a high level of assurance, consideration of the stochastic relationship between the input and output data may be very important. Variance is one of the effective parameters to deal with the stochastic relationship. This paper presents a new algroithm for a multilayer feedforward network to learn the variance of dispersed data without preliminary calculation of variance. In this paper, the network with this learning algorithm is named as a variance learning neural network(VALEAN). Computer simulation examples are utilized for the demonstration and the evaluation of VALEAN.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제25권4호
• /
• pp.162-172
• /
• 2021

This paper proposes stochastic methods to find an approximate solution for the L²-Wasserstein least squares problem of Gaussian measures. The variable for the problem is in a set of positive definite matrices. The first proposed stochastic method is a type of classical stochastic gradient methods combined with projection and the second one is a type of variance reduced methods with projection. Their global convergence are analyzed by using the framework of proximal stochastic gradient methods. The convergence of the classical stochastic gradient method combined with projection is established by using diminishing learning rate rule in which the learning rate decreases as the epoch increases but that of the variance reduced method with projection can be established by using constant learning rate. The numerical results show that the present algorithms with a proper learning rate outperforms a gradient projection method.

• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.91-98
• /
• 2011

In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV) algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.

• 영어어문교육
• /
• 제5호
• /
• pp.1-25
• /
• 1999

The objective of the present study was to model the relationships between language learning strategy use and language proficiency among the Asian (Korean, Japanese, and Taiwanese) students studying English in the United States. The instruments were a language learning strategy Questionnaire and the Institutional Testing Program Test of English as a Foreign Language (ITP TOEFL). Structural equation modeling was utilized to model the relationships between language learning strategies and language proficiency. The present study found only weak relationships between language learning strategies and language proficiency. Only 13% and 15% of variance of the listening and grammar/reading factor were explained by the language learning strategies. The metacognitive strategies appeared not to have direct relationships to the language skill factors, as was found in other studies (Purpura, 1996, 1997). The effects of the social and affective strategies were very small. They in combination could account about 1% and 4% of the variance of the listening and grammar/reading factors.

• 전기학회논문지
• /
• 제66권7호
• /
• pp.1100-1104
• /
• 2017

A detector-based approach shows the limited performances for the defect inspections such as shallow fine cracks and indistinguishable defects from background. Deep learning technique is widely used for object recognition and it's applications to detect defects have been gradually attempted. Deep learning requires huge scale of learning data, but acquisition of data can be limited in some industrial application. The possibility of applying CNN which is one of the deep learning approaches for surface defect inspection is investigated for industrial parts whose detection difficulty is challenging and learning data is not sufficient. VOV is adopted for pre-processing and to obtain a resonable number of ROIs for a data augmentation. Then CNN method is applied for the classification. Three CNN networks, AlexNet, VGGNet, and mofified VGGNet are compared for experiments of defects detection.

• 대한산업공학회지
• /
• 제28권1호
• /
• pp.112-127
• /
• 2002

A useful pattern is a pattern that contributes much to learning. For a classification problem those patterns near the class boundary surfaces carry more information to the classifier. For a regression problem the ones near the estimated surface carry more information. In both cases, the usefulness is defined only for those patterns either without error or with negligible error. Using only the useful patterns gives several benefits. First, computational complexity in memory and time for learning is decreased. Second, overfitting is avoided even when the learner is over-sized. Third, learning results in more stable learners. In this paper, we propose a pattern 'utility index' that measures the utility of an individual pattern. The utility index is based on the bias and variance of a pattern trained by a network ensemble. In classification, the pattern with a low bias and a high variance gets a high score. In regression, on the other hand, the one with a low bias and a low variance gets a high score. Based on the distribution of the utility index, the original training set is divided into a high-score group and a low-score group. Only the high-score group is then used for training. The proposed method is tested on synthetic and real-world benchmark datasets. The proposed approach gives a better or at least similar performance.

• 한국시뮬레이션학회논문지
• /
• 제14권4호
• /
• pp.9-18
• /
• 2005

In this paper, the system is implemented in four ways , For those who want to learn Chinese characters using the internet, and To make the learning more interesting and entertaining. Four different learning methods have been provided , using the transition process of Chinese characters, games, animations, and an illustration of the relationships between Chinese Characters and korean letters. The subjects of the evaluation were freshmen polled about the Chinese character learning system. The evaluation methods are : the validity of the research content is evaluated using the Cronbach's coefficient alpha and the performance of the system is evaluated by F-type of Analysis of variance.

• 대한간호학회지
• /
• 제40권2호
• /
• pp.182-190
• /
• 2010

Purpose: This study was done to identify self-directed learning readiness, achievement goal orientations, learning satisfaction and learning achievement, and to evaluate the factors affecting learning achievement for nursing students using a web-based Health Assessment e-Book. Methods: The research design was a cross-sectional study with a structured questionnaire and data were collected before using the web-based Health Assessment e-Book and 1 week after finishing. The participants were 80 nursing students who were taking the Health Assessment class from March to June 2009. Results: Mean score for subjective learning achievement was 31.26 and for objective learning achievement, 69.25. Subjective and objective learning achievement were positively correlated with self-directed learning readiness, mastery goal, attitude toward distance education, and learning satisfaction. In subjective learning achievement, learning satisfaction and mastery goal were significant predictive factors and explained 64% of the variance. Objective learning achievement was significantly predicted by learning satisfaction and self-directed learning readiness, which explained 24% of the variance. Conclusion: Learning satisfaction, mastery goal and self-directed learning readiness were found to be very important factors associated with learning achievement for nursing students using a web-based Health Assessment e-Book. To provide high quality and effective web-based courses and to improve nursing students' learning achievement and learning satisfaction, educators should consider the learner's characteristics from the initial stages of lecture planning.

• International Journal of Advanced Culture Technology
• /
• 제7권2호
• /
• pp.209-217
• /
• 2019

Due to the development of artificial intelligence and image recognition technology that play important roles in the field of 4th industry, office automation systems and unmanned automation systems are rapidly spreading in human society. The proposed algorithm first finds the variances of the differences between the tile values constituting the learning characters and the experimental character and then recognizes the experimental character according to the distribution of the three learning characters with the smallest variances. In more detail, for 100 learning data characters and 10 experimental data characters, each character is defined as the number of black pixels belonging to 15 tile areas. For each character constituting the experimental data, the variance of the differences of the tile values of 100 learning data characters is obtained and then arranged in the ascending order. After that, three learning data characters with the minimum variance values are selected, and the final recognition result for the given experimental character is selected according to the distribution of these character types. Moreover, we compare the recognition result with the result made by a neural network of basic structure. It is confirmed that satisfactory recognition results are obtained through the processes that subdivide the learning characters and experiment characters into tile sizes and then select the recognition result using variances.