• Proceedings of the Korea Information Processing Society Conference
• /
• 2023.05a
• /
• pp.60-62
• /
• 2023

인공지능의 학습 작업은 연산량이 많아 고성능 연산 장치인 GPU(Graphics Processing Unit)를 필요로 하며, GPU 장치의 성능은 학습 작업의 실행 성능에 직접적으로 영향을 미치는 요소 중 하나로 작용한다. 인공지능 작업을 처리하기 위해 많이 사용되는 텐서플로의 경우 GPU를 사용해 연산을 수행할 때 기본적으로 거의 모든 GPU 메모리 영역을 단일 학습 작업이 점유하도록 GPU 메모리를 관리한다. 이 방법은 컴퓨팅 자원 중 확장성이 가장 낮은 GPU 메모리의 단편화를 방지하기 위해 사용되는 방법이지만, 하나의 학습 작업이 GPU를 점유하게 되면, 실제 GPU 메모리 사용량과 상관없이 다른 프로세스는 GPU를 사용할 수 없는 문제를 유발한다. 특히, 전이학습, 소규모 학습과 같이 상대적으로 작업 규모가 작은 경우에는 전체 GPU 메모리 용량 중 대부분의 영역이 낭비된다. 본 논문에서는 컨테이너 환경에서 텐서플로의 기본 GPU 메모리 사용 방식으로 인해 다수의 학습 작업을 동시 실행하는 것이 불가능한 문제를 확인하고 GPU 메모리 사용량을 제한한 경우와 하지 않은 경우에 실제 GPU 메모리 사용량과 학습 작업의 실행 시간에 대한 성능 비교를 통해 GPU 메모리의 단편화 방지가 성능에 유의미한 요소인지 검증한다.

• The Journal of Korean Association of Computer Education
• /
• v.8 no.1
• /
• pp.55-63
• /
• 2005

Recently, web-based E-learning systems have entered the spotlight by providing new learning environments that break down spatial and temporal limitations. The key to building the web-based E-learning system is in determining how to effectively use the system and to evaluate the degree of learning achieved by the students that use it. In traditional off-line learning systems, we can evaluate students by counting how many questions, designed to evaluate their learning achievement, he or she answers correctly within a predetermined time limit. But this method would make individualized learning, a strong point of E-learning systems, impossible because these systems provide same learning strategy to all students even though they achieve a different level of learning. Therefore, in this paper, I will find any relationships between given test answers using fuzzy implication theory, I call these fuzzy correlations, and then generate evaluation results that are reflected in those relationships. I will compare the differences between this evaluation method and a traditional evaluation method where a student takes a test to evaluate his or her learning achievement after some learning period. Finally, I will discuss how we can use these results in individualized learning.

• Journal of the Korea Society of Computer and Information
• /
• v.25 no.9
• /
• pp.101-108
• /
• 2020

Recommender system is a must-have feature of e-commerce, since it provides customers with convenience in selecting products. Collaborative filtering is a widely-used and representative technique, where it gives recommendation lists of products preferred by other users or preferred by the current user in the past. Recently, researches on the recommendation system using deep learning artificial intelligence technologies are actively being conducted to achieve performance improvement. This study develops a collaborative filtering based recommender system using restricted Boltzmann machines of the deep learning technology by utilizing user ratings. Moreover, a learning parameter update algorithm is proposed for learning efficiency and performance. Performance evaluation of the proposed system is made through experimental analysis and comparison with conventional collaborative filtering methods. It is found that the proposed algorithm yields superior performance than the basic restricted Boltzmann machines.

• The KIPS Transactions:PartA
• /
• v.10A no.5
• /
• pp.539-550
• /
• 2003

As the service of mobile internet has been expended, student users are increase. The computers have been widely used in a education field as the teaching tool by improvement of the multimedia contents processing and user interface. The English learning using the computers in the restricted education environment provides motivations and effective learning to learners, but still have some problem such as teaching and evaluating without consideration for differences of individual levels. In order to solve the problems and take the advantages, we propose the intelligent tutoring system for english learning with mobile technology. Overcoming limitations of the mobile environment and using proper treacher's roles,. We have applied the conventional estimation method of the intellectual learner level for students. Also, we have proposed the diagnostic function in order to determine the method of teaching-learing and item disposition that each leaner prefers. Then we have designed and implemented the expert module, providing the feedback for teaching, of the intelligent turoring system for mobile english learning. This system will be able to support the interaction between teachers and students and replace some roles of teacher in the mobile english learning.

• The Journal of Korean Association of Computer Education
• /
• v.7 no.1
• /
• pp.107-118
• /
• 2004

This study aims to design and implement individual complete learning system based on IPI(Individually Prescribed Instruction) model. Most of current web based learning systems do not consider individual students' ability and just follow the sequence of instructing contents $\rightarrow$ providing problems $\rightarrow$ presenting the result of evaluating. However, this system focuses on individual ability prior to studying subjects. In individual complete learning system, it is acknowledged that a period and a pace to complete each task will differ from students to students, therefore until they complete the whole unit, they are not allowed to move onto the next unit. After completing each unit, there will be a process of evaluating students' performance. It is necessary to show the correct completion of 80% of the evaluation to move onto next step; for those who are evaluated as inadequate to move on, an individual supplementary instruction will be provided. Therefore, this study intends to supplement the deficit of prior learning and provide feedback dependent on individual's learning ability so that the goal of Individual Whole Complete Learning could be accomplished.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2020.07a
• /
• pp.664-666
• /
• 2020

데이터의 다양성은 학습에 따른 모델의 성능을 좌지우지하는 중요한 요소이다. 그렇기 때문에 많은 양의 데이터를 확보하는 것은 학습에 있어서 아주 중요하다. 하지만, 데이터를 수집하는 것은 시간과 비용이 많이 드는 단계 중 하나이다. 본 논문에서는 제한된 데이터를 가지고 이미지 처리를 거쳐 대량의 데이터로 증폭시켜 많은 양의 데이터를 확보하는 과정에 대해 제안한다. 가지고 있는 YOLOv4용 학습 데이터 셋을 활용하여 사용자로부터 입력받은 확대/축소 비율, 각도로 데이터를 변형하고, 이렇게 추가로 생성된 데이터 셋을 기존 학습 데이터 셋에 재포함시키는 소프트웨어를 개발하는 것을 목표로 한다. 구현된 소프트웨어로 증폭된 대량의 데이터 셋을 다시 원본 학습 데이터 셋에 추가하고, 같은 영상에 대해서 원본 데이터 셋만 학습시킨 경우의 객체 검출 결과와 증폭된 학습 데이터 셋이 포함된 데이터 셋의 경우의 객체 검출 결과를 비교하여 그 성능을 검증하고 분석하도록 한다.

• Journal of the Korean Society for Library and Information Science
• /
• v.44 no.4
• /
• pp.277-301
• /
• 2010

Since the England's Parliament revised the British copyright law and enacted the first copyright exception specifically for libraries (user or service) in 1956, copyright exceptions applicable to libraries have been an important part of world copyright laws through the last few decades. Copyright exceptions for libraries are a critical legal tool to preserve intellectual and cultural heritage, promote equitable access to knowledge and information to the public, and to support learning and research. Based on these reasons, this study analyzed and compared the current state of copyright structure and limitations or exceptions for library in six major countries(United States, United Kingdom, Germany, France, Japan, and Republic of Korea).

• The KIPS Transactions:PartA
• /
• v.12A no.6 s.96
• /
• pp.547-556
• /
• 2005

Online collaborative teaming, which has emerged as a new type of education in knowledge-based society, is being discussed actively in the areas of action learning at companies and project-based learning and inquiry-based learning at schools. It regards as an effective method for improving learners practical and highly advanced problem solving abilities, and for stimulating their absorption into learning through pursuing common goals of learning together. Different from individual learning, however, collaborative learning involves complicated processes such as organizing teams, setting common goals, performing tasks and evaluating the outcome of team activities .Thus, it is difficult for a teacher to promote and evaluate the whole process of collaborative learning, and it is necessary to develop systems to support collaborative learning. Therefore, in order to monitor and promote interaction among learners in the process of collaborative learning, the present study developed an extensible collaborative teaming supporting agent (ECOLA) in online learning environments.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.10d
• /
• pp.361-363
• /
• 2002

Version space는 목표 개념이 속성 값에 대한 제한조건의 연언(conjunction)으로 표현될 수 있는 귀납적 개념학습에서 가설공간을 표현하기 위해 사용된다. Version space의 크기는 속성 값의 수에 대해 지수적으로 증가하는데, 우리는 DNA 분자를 이용하여 version space를 표현하는 효율적인 방법을 제시한다. 또한 version space를 유지하기 위한 기본 연산과, 이를 DNA 분자를 이용하는 구현 방법이 제시된다. 또한 DNA 분자로 표현된 version space를 활용하여 새로운 example에 대한 분류를 예측하는 방법을 제시한다.

• Proceedings of the Korean Information Science Society Conference
• /
• 2002.04b
• /
• pp.490-492
• /
• 2002

본 논문에서는 필터링 문제를 이진 문서 분류 문제로 보고 신문기사 필터링에 베이지안 분류자를 사용한다. 신문 기사 필터링 문제에서 베이지안 분류자를 사용할 경우 학습 문서가 고정되어 있지 않기 때문에 여러 가지 파라미터를 사용하여 실험을 하였다. 실험 결과 베이지안 이진 분류기는 제한된 학습 문서에서 더 나은 성능을 보였고 해당 문서 집합에서 10%이상 비율의 문서를 사용자가 선택해야 함을 알 수 있었다.