• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2002년도 ICCAS
• /
• pp.42.6-42
• /
• 2002

Kohonen's self organizing feature map (SOFM) converts arbitrary dimensional patterns into one or two dimensional arrays of nodes. Among the many competitive learning algorithms, SOFM proposed by Kohonen is considered to be powerful in the sense that it not only clusters the input pattern adaptively but also organize the output node topologically. SOFM is usually used for a preprocessor or cluster. It can perform dimensional reduction of input patterns and obtain a topology-preserving map that preserves neighborhood relations of the input patterns. The traditional SOFM algorithm[1] is a competitive learning neural network that maps inputs to discrete points that are called nodes on a lattice...

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1997년도 추계학술대회 논문집 학회본부
• /
• pp.591-593
• /
• 1997

When input circumstance is changed abrubtly, many nodes of Competitive Learning Neural Networks far from new input vector may never win, and therefore never learn. Various techniques to prevent these phenomena have been reported. We proposed a new technique based on Self Creating and Organizing Neural Networks, and which is compared to Self Organizing Feature Map and Frequency Sensitive Neural Networks.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2806-2825
• /
• 2018

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm ($L_2$) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.

• 대한산업공학회지
• /
• 제27권2호
• /
• pp.214-225
• /
• 2001

This research deals with an off-line learning method targeted for systematically constructing negotiation strategies in automated electronic commerce. Single-issue negotiation is assumed. Variants of competitive learning and hierarchical clustering method are devised and applied to extracting negotiation strategies, given historical negotiation data set and tactics. Our research is motivated by the following fact: evidence from both theoretical analysis and observations of human interaction shows that if decision makers have prior knowledge on the behaviors of opponents from negotiation, the overall payoff would increase. Simulation-based experiments convinced us that the proposed method is more effective than human negotiation in terms of the ratio of negotiation settlement and resulting payoff.

• 패션비즈니스
• /
• 제16권5호
• /
• pp.178-191
• /
• 2012

This paper is purposed to study on the relationship of learning style, professor image, academic achievement in cosmetology majoring college students, and to find the effective education methods of them. The research methods are survey with 400 persons & statistics analysis such as frequency, factor, regression analysis, using SPSS V.14. The results are as belows; 1. Learning styles are divided by (1) shirker, (2) participate, (3) stand-alone, (4) dependent, (5) cooperative, (6) competitive, and professor images are divided by (1) professor ability, (2) professor relationship. 2. There is a relationship in learning styles and professor images. Especially cooperative, participate, dependent valued professor ability, shirker devalued it and cooperative, stand-alone, dependent, competitive valued professor relationship, shirker devalued it. 3. There is a relationship on learning styles and the academic achievement. participate, stand-alone, dependent achieve in high glades and shirker, cooperative low ones. 4. There is a no valid relationship with professor images and the students' academic achievement. 5. The conclusion are; there are the relationship of learning style, professor image, academic achievement in cosmetology majoring college students. So shirker need endless motive giving program, participate personal record management system, dependent creative motivating program, participate class attractive factors, stand-alone learner centered program.

• 한국지능시스템학회논문지
• /
• 제10권3호
• /
• pp.203-210
• /
• 2000

본 논문에서는 패턴분류문제를 해결하기 위한 새로운 무감독학습 신경망 및 경쟁학습 알고리즘을 제한한다. 제아하는 신경망은 입력 데이터의 군집을 분류하기 위한 거리측도로서 군집들 상호간의 상대유사도(relative similarity)를 기반으로 하고 있다. 이러한 까닭에 제안하는 신경망과 알고리즘을 상대유사 신경망 (relative similarity network; RSN)및 학습 알고리즘이라 이름한다. 상대유사도를 정의하고 가중벡터 학습 규칙을 구성함으로써, RSN의 구조를 설계하고 학습알고리즘을 구현하기 의한 의사코드를 기술한다. 일반적인 패턴분류에 RSN을 적용한 결과, 초기 학습률이 없음에도 불구하고 기존이 경쟁학습 신경망인 WTAdlsk SOM고 동등한 성능을 나타내었다. 반면 기존 경쟁학습 신경망의 분류성능이 저하되었던 군집이 경걔가 불분명한 패턴, 그리고 군집이 밀집도와 군집의 크기가 다른 패턴들에 대한 실험에서는 기존의 경쟁학습망보다 효과적인 분류결과를 나타내었다.

• 컴퓨터교육학회논문지
• /
• 제5권4호
• /
• pp.1-8
• /
• 2002

인터넷기술의 발달과 네트워크 환경의 구축 및 확산은 웹을 통한 교육적 적용과 활용을 더욱 증가시켰다. 학습에 참여하는 교사와 학습자는 경쟁적, 개별적, 협동적 학습구조에 따라 교육을 진행한다. 이중 경쟁적, 개별적 학습구조가 갖고 있는 지나친 경쟁의 유발이나 학습자간 협력도의 결여라는 문제점에 대한 새로운 대안으로서 협동적 학습구조에 대한 관심이 증가되었다. 이러한 배경속에서 본 연구는 협동학습의 장점과 모형을 웹에 적용하여 기존의 웹 기반 교육사이트의 질적 향상을 기한 웹 기반 협동학습 사이트를 설계 및 구현하고, 실시된 웹 기반 협동학습에 대한 실험연구를 통하여 협동학습에 참여한 학습자들의 학업성취도와 동기-태도를 향상시키고 있음을 보인다.

• 한국정보시스템학회지:정보시스템연구
• /
• 제14권2호
• /
• pp.75-99
• /
• 2005

Today, many universities are confronted with the changing education paradigm such as e-learning, Distance Education, Virtual University, This IT-based teaming paradigm shift is certainly a new opportunity or a threat to our universities. To overcome this problem the universities should think e-Learning as strategic weapon, such as many firms created competitive weapons from the information systems at the 1980s. So, e-Learning system can be a SIS(Strategic Information System) which supports university's future education strategies. To build a e-Learning system, not only many H/W and S/W resources but also expert personnels are required. An organization such as local university who is week at financial status can't himself plan the system. The Local University Community e-Learning Centers that support the demand of e-learning for their community are recommended. In order to operate these centers efficiently, the strategic roles of the e-Learning center should first be defined. To define the strategic roles, We classified the strategic roles of the e-Learning center into four dimensions, (1) to improve management efficiency, (2) to enhance educational service, (3) to acquire competitive advantages, (4) to build new education infrastructure, and each dimension has 5 or 6 measurement items. As result, to enhance the educational service was considered as the most significant factor among the four dimensions of strategic roles, and the infrastructure building was the next. We also tried to find the difference for each factor by the characteristics of responsor. The data showed that there was litter difference between the groups in evaluating the significance of strategic roles of e-learning centers. Through the strategic roles definition and analysis of expected role ratings, we could have recommended the direction and operation policies of the e-Loaming centers.

• 대한전기학회논문지
• /
• 제41권5호
• /
• pp.533-540
• /
• 1992

The Self Creating and Organizing (SCO) is a new architecture and one of the unsupervized learning algorithm for the artificial neural network. SCO begins with only one output node which has a sufficiently wide response range, and the response ranges of all the nodes decrease automatically whether adapting the weights of existing node or creating a new node. It is compared to the Kohonen's Self Organizing Feature Map (SOFM). The results show that SCONN has lots of advantages over other competitive learning architecture.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1994년도 추계학술대회 논문집 학회본부
• /
• pp.326-328
• /
• 1994

A modified Kohonen's simple Competitive Learning(SCL) algorithm which has binary reinforcement function and a constant adaptation gain is proposed. In contrast to the time-varing adaptation gain of the original Kohonen's SCL algorithm, the proposed algorithm uses a constant adaptation gain, and adds a binary reinforcement function in order to compensate for the lowered learning ability of SCL due to the constant adaptation gain. Since the proposed algorithm does not have the complicated multiplication, it's digital hardware implementation is much easier than one of the original SCL.