• IEMEK Journal of Embedded Systems and Applications
• /
• v.15 no.2
• /
• pp.43-49
• /
• 2020

In this paper, we propose a stage-wise knowledge transfer method that uses block-wise retraining to transfer the useful knowledge of a pre-trained residual network (ResNet) in a teacher-student framework (TSF). First, multiple hint information transfer and block-wise supervised retraining of the information was alternatively performed between teacher and student ResNet models. Next, Softened output information-based knowledge transfer was additionally considered in the TSF. The results experimentally showed that the proposed method using multiple hint-based bottom-up knowledge transfer coupled with incremental block-wise retraining provided the improved student ResNet with higher accuracy than existing KD and hint-based knowledge transfer methods considered in this study.

• ETRI Journal
• /
• v.41 no.2
• /
• pp.242-253
• /
• 2019

We devise a layer-wise hint training method to improve the existing hint-based knowledge distillation (KD) training approach, which is employed for knowledge transfer in a teacher-student framework using a residual network (ResNet). To achieve this objective, the proposed method first iteratively trains the student ResNet and incrementally employs hint-based information extracted from the pretrained teacher ResNet containing several hint and guided layers. Next, typical softening factor-based KD training is performed using the previously estimated hint-based information. We compare the recognition accuracy of the proposed approach with that of KD training without hints, hint-based KD training, and ResNet-based layer-wise pretraining using reliable datasets, including CIFAR-10, CIFAR-100, and MNIST. When using the selected multiple hint-based information items and their layer-wise transfer in the proposed method, the trained student ResNet more accurately reflects the pretrained teacher ResNet's rich information than the baseline training methods, for all the benchmark datasets we consider in this study.

• Journal of Korea Multimedia Society
• /
• v.24 no.12
• /
• pp.1598-1605
• /
• 2021

Recently, convolutional neural networks (CNNs) have been widely used with excellent performance in various computer vision fields, including super-resolution (SR). However, CNN is computationally intensive and requires a lot of memory, making it difficult to apply to limited hardware resources such as mobile or Internet of Things devices. To solve these limitations, network lightening studies have been actively conducted to reduce the depth or size of pre-trained deep CNN models while maintaining their performance as much as possible. This paper aims to lighten the SR CNN model, SRGAN, using the knowledge distillation among network lightening technologies; thus, it proposes four techniques with different methods of transferring the knowledge of the teacher network to the student network and presents experiments to compare and analyze the performance of each technique. In our experimental results, it was confirmed through quantitative and qualitative evaluation indicators that student networks with knowledge transfer performed better than those without knowledge transfer, and among the four knowledge transfer techniques, the technique of conducting adversarial learning after transferring knowledge from the teacher generator to the student generator showed the best performance.

• Journal of Engineering Education Research
• /
• v.10 no.2
• /
• pp.87-105
• /
• 2007

In this research, Integrated program base on heat transfer & numerical analysis was developed. Also, reaction of gifted student and possibility of application of this program was surveyed. This program consist in three parts. The first part is computer programing language, the second part is numerical modeling of physical phenomena, and the third part is numerical analysis. 4 students are selected who belong to mathematic class of CNUE(Cheoungju National Univ. of Edu.)'s Gifted Student Education Center. The Program consists in 15th lessens, and each lessen need 4hr. Application possibility and student's satisfaction of the program are studied through the interview and report of the student. Three of four students are accomplish the goal of the progarm. Computer programing and numerical analysis parts were relatively well understood, but numerical modeling part was difficult to students. The satisfaction of the program is dependent on the characteristics of the student. Most of the student thought that this program was one of the science education program. The student who have interested in only mathematics shows that low satisfaction but the one who have interested in science or information technology shows that high satisfaction.

• Journal of Mechanical Science and Technology
• /
• v.15 no.6
• /
• pp.752-763
• /
• 2001

Although there are many different solution schemes proposed for multidimensional radiative transfer, reference solutions to benchmark these methods are very rare in the literature. In this paper we produced some accurate solutions for purely absorbing gray and nongray gases including H$_2$O and CO$_2$by using the discrete transfer method with sufficiently accurate T(sub)95 quadrature set. The spectral transmittances of the mixtures of H$_2$O and CO$_2$are estimated by using the narrow band model. The gray gas solutions are obtained for different absorption coefficients, and the nongray real gas solutions are obtained for different mixture fractions of H$_2$O and CO$_2$. The numerical solutions presented in this paper are proved to be sufficiently accurate as compared to the available exact solutions and they may be used as reference solutions in evaluating various solution schemes.

• ETRI Journal
• /
• v.46 no.1
• /
• pp.59-70
• /
• 2024

We introduce a high-performance named entity recognition (NER) model for written and spoken language. To overcome challenges related to labeled data scarcity and domain shifts, we use transfer learning to leverage our previously developed KorBERT as the base model. We also adopt a meta-pseudo-label method using a teacher/student framework with labeled and unlabeled data. Our model presents two modifications. First, the student model is updated with an average loss from both human- and pseudo-labeled data. Second, the influence of noisy pseudo-labeled data is mitigated by considering feedback scores and updating the teacher model only when below a threshold (0.0005). We achieve the target NER performance in the spoken language domain and improve that in the written language domain by proposing a straightforward rollback method that reverts to the best model based on scarce human-labeled data. Further improvement is achieved by adjusting the label vector weights in the named entity dictionary.

• Journal of Yeungnam Medical Science
• /
• v.34 no.1
• /
• pp.62-68
• /
• 2017

Background: This study was conducted to examine the academic achievements of first year medical students in one medical school based on their characteristics and student selection factors of admission. Methods: The admission scores of student selection factors (Medical Education Eligibility Test [MEET], grade point average [GPA], English test score and interview) and demographic information were obtained from 61 students who had interviewed (multiple mini interview [MMI]) for admission (38 graduate medical school students in 2014, 23 medical college-transfer students in 2015). T-tests and ANOVA were used to examine the differences in academic achievement according to the student characteristics. Correlations between admission criteria scores and academic achievements were examined. Results: MEET score was higher among graduate medical students than medical college transfer students among student selection factors for admission. There were no significant differences in academic achievement of first grade medical school between age, gender, region of high school, years after graduation and school system. The lowest interview score group showed significantly lower achievement in problem-based learning (PBL) (p=0.034). Undergraduate GPA score was positively correlated with first grade total score (r=0.446, p=0.001) among admission scores of student selection factors. Conclusion: Students with higher GPA scores tend to do better academically in their first year of medical school. In case of interview, academic achievement did not lead to differences except for PBL.

• Journal of the Korea Convergence Society
• /
• v.12 no.11
• /
• pp.35-43
• /
• 2021

Recently, there has been a growing interest in zero-shot cross-lingual transfer, which leverages cross-lingual language models (CLLMs) to perform downstream tasks that are not trained in a specific language. In this paper, we point out the limitations of the data-centric aspect of quality estimation (QE), and perform zero-shot cross-lingual transfer even in environments where it is difficult to construct QE data. Few studies have dealt with zero-shots in QE, and after fine-tuning the English-German QE dataset, we perform zero-shot transfer leveraging CLLMs. We conduct comparative analysis between various CLLMs. We also perform zero-shot transfer on language pairs with different sized resources and analyze results based on the linguistic characteristics of each language. Experimental results showed the highest performance in multilingual BART and multillingual BERT, and we induced QE to be performed even when QE learning for a specific language pair was not performed at all.

• The Journal of the Korea Contents Association
• /
• v.17 no.11
• /
• pp.123-134
• /
• 2017

This study examines the Korean Education Longitudinal Study 2005 7th-9th year data to analyze the university life of transfer students prior to their transferring by comparing them to that of non-transfer students. This study used two types of comparison groups: The first comparison group encompasses all who did not transfer and the second group was 1:1 matched sample of students who were enrolled in the same universities in the 7th year and were of the same gender. The 7th and 8th year experiences were compared, respectively. According to the result, transfer students in their previous universities compared to non-transfer students demonstrated higher grade point average, active class participation, and more interaction with faculty outside the class. On the other hand, these students demonstrated relatively lower satisfaction in university life, lower sense of belonging, and lower participation in student unions, campus events, and other student activities. They also tended to have less interaction with their colleagues. In other words, transfer students showed high competency and interests in academic activities like managing good grades and interacting with faculty but showed less interest in social activities such as interacting with peers and engaging in various campus activities. It is necessary to develope programs to help transfer students to adapt to school efficiently by utilizing the results of this study.

• Journal of the Korean Data and Information Science Society
• /
• v.14 no.1
• /
• pp.11-21
• /
• 2003

In 1997 a new educational system that allows student to transfer between and within universities was first introduced. As a result, most colleges of basic arts and sciences face a serious problem since quite a few students there have transferred or seems to want to transfer. In this paper we study a problem of building a forecasting neural network for students who can possibly transfer.