• 경영과학
• /
• 제18권2호
• /
• pp.25-38
• /
• 2001

The well-known back-propagation algorithm for multi-layered neural network has successfully been applied to pattern c1assification problems with remarkable flexibility. Recently. the multi-layered neural network is used as a powerful data mining tool. Nevertheless, in many cases with complex boundary of classification, the successful learning is not guaranteed and the problems of long learning time and local minimum attraction restrict the field application. In this paper, an Improved learning procedure of multi-layered neural network is proposed. The procedure is based on the generalized delta rule but it is particular in the point that the architecture of network is not fixed but enlarged during learning. That is, the number of hidden nodes or hidden layers are increased to help finding the classification boundary and such procedure is controlled by entropy evaluation. The learning speed and the pattern classification performance are analyzed and compared with the back-propagation algorithm.

• 한국건축시공학회지
• /
• 제13권1호
• /
• pp.10-19
• /
• 2013

Companies want universities to produce graduates with creativity and problem-solving skills, and for this reason universities have extended engineering design education, including in the field of architectural engineering. This paper investigates an engineering design class in the Department of Architectural Engineering, J University. The class was taught in 2010 and 2011using an Action Learning (AL) teaching-learning strategy. The students responded that the level of participation and satisfaction was high in the Action Learning classes, and role allocation or responsibility and communication of the project teams were very effective. But it was also found that as Action Learning is such a new method for students of engineering design, an orientation session that describes what to do and what to prepare should be given before the class starts.

• 한국산학기술학회논문지
• /
• 제8권6호
• /
• pp.1673-1681
• /
• 2007

본 연구에서는 차세대 고부가가치 지식산업이 될 u-러닝에 대한 개념, 그리고 국내 외 u-러닝 시장 동향 및 u-러닝 산업추진상의 문제점을 살펴보았다. 이와 더불어 국내 u-러닝 산업의 SWOT 분석을 통해 국내 산업 경쟁력 확보하기 위한 정책과제 및 추진방향을 도출하였다.

• 디지털산업정보학회논문지
• /
• 제9권4호
• /
• pp.177-188
• /
• 2013

Since the world entered the age called "Smart Revolution", there has also been a lot of changes in the field of education. In educational environment, there is a growing interest in smart learning based on mobile contents, with the development of Smart Devices and ubiquitous technology. This paper is about a research on what effects smart learning has on leaner side when learners make active use of mobile contents in this age of Smart Revolution. First, we embodied teaching plans for some practical classes in forms of mobile contents using M-bizmaker. After the learning process based on the embodied contents for students, we analyzed the survey results on 4 sections-their use of apps, screen composition, technical support, interactions. We also studied the results of a questionnaire on 4 sections-contents, information offering, feedback systems, learner assessment-to evaluate their satisfaction. The research suggests that learner satisfaction can be improved with smart learning based on mobile contents embodied for leaners.

• 정보과학회 논문지
• /
• 제43권7호
• /
• pp.751-762
• /
• 2016

본고에서는 양자역학 기반의 기계학습인 양자 기계학습의 현황과 전망을 조망하고자 한다. 양자역학 기반의 양자컴퓨팅이 보여준 혁신적인 계산속도 개선에 힘입어 기계학습 분야에 양자컴퓨팅 알고리즘을 적용하는 연구는 빅데이터 시대의 도래에 따라 최근 집중적인 관심을 받고 있다. 고전적인 기계학습 알고리즘들에 양자컴퓨팅을 접목하여 획기적인 속도개선을 가능하게 하는 알고리즘 연구들과 최초의 상용 양자컴퓨터로 화제가 되고 있는 양자 담금질 알고리즘 등을 중심으로 양자 기계학습의 최신동향과 가능성을 살펴보고자 한다.

• East Asian mathematical journal
• /
• 제40권2호
• /
• pp.231-265
• /
• 2024

Achieving something in learning is a very important task. Due to its significance, extensive research has been conducted over a long period to determine what factors influence learning. In the field of mathematics, such research has been continuously carried out, and as a result, it has been revealed that cognitive, affective, and socio-environmental factors influence mathematics learning. However, most of these studies were based on one or two variables, and thus, they did not comprehensively examine the factors affecting mathematics learning. Therefore, this study aims to synthesize the existing research to comprehensively derive the factors influencing mathematics learning.

• International Journal of Internet, Broadcasting and Communication
• /
• 제16권2호
• /
• pp.127-135
• /
• 2024

Recent studies have shown that inverse design using deep learning has the potential to rapidly generate the optimal design that satisfies the target performance without the need for iterative optimization processes. Unlike traditional methods, deep learning allows the network to rapidly generate a large number of solution candidates for the same objective after a single training, and enables the generation of diverse designs tailored to the objectives of inverse design. These inverse design techniques are expected to significantly enhance the efficiency and innovation of design processes in various fields such as aerospace, biology, medical, and engineering. We analyzes inverse design models that are mainly utilized in the nano and chemical fields, and proposes inverse design models based on supervised and unsupervised learning that can be applied to the engineering system. It is expected to present the possibility of effectively applying inverse design methodologies to the design optimization problem in the field of engineering according to each specific objective.

• 전기학회논문지P
• /
• 제65권4호
• /
• pp.309-315
• /
• 2016

NCS is the nation-wide standard designed to standardize and systematize the capability(knowledge, technology and attitude) required for personnel to undertake their task in industrial site according to industry field and level of the task. In order to cope with rapidly changing labor market, individual has to be equipped with ability required for each relevant duty field. And company also requires worker to have basic working ability, professional knowledge or technical capability for relevant duty. Especially, the core competency, a fundamental element for all tasks, has been recognized as critical part not just in social level but also in company level. In that sense, the necessity of adding the core competence into regular education program has been vastly demanded. This study mainly deals with development of NCS-based learning module for information capability that most of industrial field want their employee to be equipped as basic skill. And, in particular, education achievement analysis for computer application capability, a subordinate capabilities of information capability, and its application method are mainly described.

• 한국산업융합학회 논문집
• /
• 제23권3호
• /
• pp.481-489
• /
• 2020

Safety and security during the handling of hazardous materials is a great concern for anyone in the field. One driving point in the security field is the ability to detect the source of the danger and take action against it as quickly as possible. Via the usage of a fully convolutional network, it is possible to create the label map of an input image, indicating what object is occupying the specific area of the image. This research employs the usage of U-net, which was constructed in biomedical field segmentation to segment cells, instead of the original FCN. One of the challenges that this research faces is the availability of ground truth with precise labeling for the dataset. Testing the network after training resulted in some images where the network pronounces even better detail than the expected label map. With better detailed label map, the network might be able to produce better segmentation is something to be studied in further research.

• 한국과학교육학회지
• /
• 제19권3호
• /
• pp.471-478
• /
• 1999

In this study, the relationships among learners' cognitive variables, motivational variables, and conceptual understandings in learning with analogy were investigated. The instruments regarding analogical reasoning ability, field dependence-independence, mental capacity, and logical thinking ability were administered. Some subtests (self-efficacy, expectancy, self-concept of ability, and value) of the Patterns of Adaptive Learning Survey were administered. After students learned with a worksheet that included analogy, a conception test regarding 'stoichiometry that included limiting reagent' was also administered. It was found that learners' conceptual understandings were significantly correlated with the logical thinking ability and the field dependence-independence among the cognitive variables, and the self-efficacy and the self-concept of ability among the motivational variables. The multiple regression analysis of the cognitive variables on conceptual understandings revealed that the logical thinking ability was the most significant predictor. The field dependence-independence also had predictive power. In the analysis of the motivational variables, the self concept of ability was the only significant predictor.