• 대한전기학회논문지
• /
• 제41권3호
• /
• pp.274-280
• /
• 1992

In this paper, an Improved Error Back Propagation Algorithm is introduced, which avoids Network Paralysis, one of the problems of the Error Backpropagation learning rule. For this purpose, we analyzed the reason for Network Paralysis and modified the Activation Function Derivative of the standard Error Backpropagation Algorithm which is regarded as the cause of the phenomenon. The characteristics of the modified Activation Function Derivative is analyzed. The performance of the modified Error Backpropagation Algorithm is shown to be better than that of the standard Error Back Propagation algorithm by various experiments.

• The Journal of the Acoustical Society of Korea
• /
• 제17권1E호
• /
• pp.36-43
• /
• 1998

A fuzzy logic filter is constructed from a set of fuzzy IF-THEN rules which change adaptively to minimize some criterion function as new information becomes available. This paper generalizes the fuzzy logic filter and it's adaptive filtering algorithm to include complex parameters and complex signals. Using the complex Stone-Weierstrass theorem, we prove that linear combinations of the fuzzy basis functions are capable of uniformly approximating and complex continuous function on a compact set to arbitrary accuracy. Based on the fuzzy basis function representations, a complex orthogonal least-squares (COLS) learning algorithm is developed for designing fuzzy systems based on given input-output pairs. Also, we propose an adaptive algorithm based on LMS which adjust simultaneously filter parameters and the parameter of the membership function which characterize the fuzzy concepts in the IF-THEN rules. The modeling of a nonlinear communications channel based on a complex fuzzy is used to demonstrate the effectiveness of these algorithm.

• 대한공업교육학회지
• /
• 제30권1호
• /
• pp.19-36
• /
• 2005

The purpose of this study is to develop the Public Practice Center's teaching-learning model by applying blended learning strategies which is complementary to the expected problems such as expansion of the educational object and diversity of the curriculum to maximize the educational effect and to analyze activation types of the Practical Practice Center to expand the Public Practice Center's function and role by studying the document. Blended Learning Strategies are established in consideration of the following eight (8) factors ; learning environment, learning purpose, learning contents, learning time, learning place, learning type, learning media, type of interaction. It is redesigned and amended to the KEDI's individual confirmation instruction model for skill learning (1975) which is considered to be effective in the filed of education by applying features, educational contents of the Public Practice Center's teaching and merit of Blended Learning Strategies simultaneous. This model is composed of six (6) steps as shown below; 1. Understanding on the purpose and orientation 2. Observation for demonstration of fundamental skill 3. Ex on-line learning 4. Acquirement of element skill 5. Confirmation for acquirement of fundamental skill 6. After on-line learning. Further to this, this model is designed so that the above eight factors will be applied to the students effectively and the merit of e-learning and off-line practice will be mixed to the learner's expectation and satisfaction.

• 대한한의학회지
• /
• 제20권4호
• /
• pp.39-49
• /
• 2000

This study was conducted to prove that there exists a relation between the spleen and learning and memory as Oriental medicine believesTo promote the function of the Spleen, Guibitang was administered to rats in this study. Rats were 250～300g Sprague-Dawley, and were divided into three groups. One was the normal group without any pretreatment. Another was the control group which was administered normal saline and the abdominal injection of L-NAME before learning and memory test. And the 3rd was the sample group, to which was administered Guibitang extract and (no 'the') abdominal injection of L-NAME before the learning and memory test. Each group was made up of 12 rats. Morris water maze and radial arm maze tasks were performed in the learning test and Morris water maze task in the memory test. For 2 days to evaluate the ability of learning in the Morris water maze, 16 trials were carried out and first latency(lapse time to find the escape platform for the first time) was measured. The next day, to evaluate the ability of memory, the escape platform was eliminated from the maze, and total path, target entry number, first latency and memory score were measured. 48hrs before the radial arm maze task was performed, bait was deprived from each group. After learning test, bait was permitted to each group. So 85% of the body weight was maintained for 6 days of the test. Each of the eight arms was baited; correct choice numer and error were counted; each trial was finished when the rat had entered each of the eight arms, or more than 10 minutes had elapsed. The results were as follows: In the learning test, the first latency of the sample group in the Morris water maze showed evident improvement of learning compared to control group at the 11th, 12th, 13th trial of 16 trials, and correct choice number in radial arm maze showed noticeable improvement compared to the control group at 3rd, 4th and 5th; In the memory test, the memory score of the sample group showed evident improvement compared to the control group. From the above results, the administration of Guibitang, which tonifies the function of the Spleen, could enhance the ability of learning and memory. So it was suggested that the Spleen has a relation with learning and memory.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국제학술편); Seoul National University, Seoul; 20-22 Oct. 1993
• /
• pp.395-400
• /
• 1993

This paper presents an application of back propagation neural network to the tracking control of line of sight stabilization system. We design a neuro-control system having two neural networks one for learning system dynamics and the other for control. We use a learning method which adjusts learning rate and momentem as a function of plant output error and error change.

• 한국의류학회지
• /
• 제16권1호
• /
• pp.137-146
• /
• 1992

As a preliminary work for the interrelations between individuals' learning style and their consumer decision-making styles in purchasing apparel, its theoretical backgrounds were reviewed. Several major approaches to measuring and characterizing learning styles were theories of Hunt, Schroder, Kolb, and sproles. - Relevant literature suggests several consumer decision-making styles including Morchis' and Sproles'. Researches on the practical' implication of theoretical learning styles model in the area of consumer decision-making styles were also explored.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1992년도 한국자동제어학술회의논문집(국내학술편); KOEX, Seoul; 19-21 Oct. 1992
• /
• pp.218-223
• /
• 1992

This paper describes a learning method of neural network controllers. The learning method improves the performance of indirect learning mechanism in the neuro-control of nonlinear systems. To precisely identify dynamic characteristics of the plant by utilizing a limited prior information we propose a new energy function which takes advantage of the proportional relationship between outputs of the plant and those of neural networks.

• Communications for Statistical Applications and Methods
• /
• 제19권3호
• /
• pp.433-450
• /
• 2012

연구자가 같은 작업을 반복적으로 수행할 때, 작업 효율성은 연구에 관련된 지식, 경험, 기술이 축적되면서 향상된다. 결과를 얻기 위해 연구에 투자하는 시간은 같은 작업을 반복함으로써 줄일 수 있다. 이러한 현상을 학습곡선 효과(learning curve effect)라고 일컫는다. 학습곡선(learning curves)은 학습의 변화를 시각적으로 나타낸 것으로 이전의 학습곡선 연구에서는 시간을 일정한 구간으로 나누어 구간별 작업에 대한 숙련도의 평균 차이 여부를 확인하였다. 이러한 방법은 구간을 어떻게 나눌 것인가 하는 기준이 존재하지 않으며, 더욱이 이항 반응 자료로 모형을 적합하기 어려운 문제점을 가지고 있다. 본 연구에서는 이산형 확률변수 중 이항 반응 자료(베르누이자료)에 대한 학습곡선의 통계적 모형에 초점을 맞추고자 한다. 누적확률분포의 특성을 이용하여 모수를 추정하기 위해서 뉴튼-랩슨 방법(Newton-Raphson method)을 사용하였고, 이 연구에서 제안한 모형의 점근적 분포를 구하였다.

• 한국인터넷방송통신학회논문지
• /
• 제18권1호
• /
• pp.105-111
• /
• 2018

공교육의 STEAM과 S/W 교육은 융합 인재와 4차산업혁명 시대의 인재 양성에 효과적이며 이를 위한 전담교사의 확충과 다양한 학습자료의 발굴 및 적용, 융합인재 교육을 위한 교육환경 개선이 필요하다. 그리고, 개방형 학습 플랫폼은 사교육비 절감과 공교육의 보완에 효과적이다. 특히 교실 수업(오프라인)과 결합된 플립러닝에 유용하며 이럴 경우 교사의 역할이 능동적인 교수활동과 연구 활동으로 전환되어 공교육의 정상화를 앞당기고 사교육을 줄일 수 있다. 특히, 초등교육을 위한 MOOC 플랫폼 운영의 핵심 기능으로 '창의적 교수설계와 콘텐츠 개발 기능', '디지털 교수 학습 큐레이션 기능', '빅데이터 기반 학습자 맞춤화 기능', '학습 참여 촉진 플립러닝 및 소셜러닝 기능'을 제시한다. 본 연구를 통해 초등교육을 포함한 청소년의 진로 및 입시교육 MOOC의 도입에 대한 논의의 장이 마련되고 한국형 청소년 MOOC 플랫폼이 구축되어 교육민주화의 세계적 선진 모델로 발전될 수 있기를 기대한다.

• 인터넷정보학회논문지
• /
• 제15권6호
• /
• pp.77-84
• /
• 2014

본 연구는 대학에서 이러닝을 활용 수업의 효과에 영향을 미치는 요인들을 탐색하고 요인들 간의 인과관계를 파악하고자 하였다. 이를 위해 2013년 2학기를 기준으로 이러닝 기반의 수업인 사이버 강의에 참여한 학생들 2,091명 중 유효했던 1,732명을 연구 대상으로 하였다. 연구방법은 확인적 요인분석과 구조방정식모형 분석을 활용하였다. 확인적 요인분석을 통해 이러닝 학습효과, 컨텐츠만족요인, 시스템기능요인, 운영지원요인의 네 개의 잠재변인을 도출할 수 있었다. 이들 잠재변인들 간의 구조방정식 모델 분석을 통한 결과는 다음과 같다. 첫째, 이러닝 학습효과와 관련된 주요 요인으로 컨텐츠 요인, 기능요인, 운영지원 요인으로 구분할 수 있었다. 둘째, 이러닝 학습효과에는 운영지원, 컨텐츠 요인이 직접적 영향을 미치는 것으로 나타났다. 하지만 기능요인은 유의하지 않은 것으로 나타났다. 셋째, 컨텐츠 요인에는 기능 및 운영요인이 유의한 영향을 미치는 것으로 나타났다. 넷째, 기능요인 및 운영지원요인은 컨텐츠 요인을 매개로하여 이러닝 학습효과에 간접적 영향을 미치는 것으로 나타났다.