• Journal of Information Processing Systems
• /
• 제13권4호
• /
• pp.643-652
• /
• 2017

• 한국정보시스템학회지:정보시스템연구
• /
• 제22권1호
• /
• pp.165-180
• /
• 2013

Using long-term panel data of OKCashbag, this study analyzes whether learning effect influencing in effectiveness of coalition loyalty program exists. We found that there is learning effect in the behavior of loyalty program customers, and discovered that learning effect appears more greatly in using (redeeming) behavior than accumulating behavior. The authors also found a long-lasting structural changes in the pattern of point redemption after a major marketing activities associated with the act of using points. The results of this research can contribute to suggest direction to the future researches to examine differences of learning effect according to demographic (gender, age, region, ect.) and transactional (frequency or scale in point accumulation and redemption etc.) characteristics.

• 전자공학회논문지B
• /
• 제29B권4호
• /
• pp.58-65
• /
• 1992

In this paper new back propagation algorithm which adds neurons to hidden layer is proposed. this proposed algorithm is applied to the pattern recognition of written number coupled with back propagation algorithm through omitting redundant learning. Learning rate and recognition rate of the proposed algorithm are compared with those of the conventional back propagation algorithm and the back propagation through omitting redundant learning. The learning rate of proposed algorithm is 4 times as fast as the conventional back propagation algorithm and 2 times as fast as the back propagation through omitting redundant learning. The recognition rate is 96.2% in case of the conventional back propagation algorithm, 96.5% in case of the back propagation through omitting redundant learning and 97.4% in the proposed algorithm.

• 제어로봇시스템학회논문지
• /
• 제17권8호
• /
• pp.777-782
• /
• 2011

Neural network technique is widely employed in the fields of signal processing, control systems, pattern recognition, etc. Learning of neural networks is an important procedure to accomplish dynamic system modeling. This paper presents a novel learning approach for differential neural network models based on the Kalman-Bucy filter theory. We construct an augmented state vector including original neural state and parameter vectors and derive a state estimation rule avoiding gradient function terms which involve to the conventional neural learning methods such as a back-propagation approach. We carry out numerical simulation to evaluate the proposed learning approach in nonlinear system modeling. By comparing to the well-known back-propagation approach and Kalman-Bucy filtering, its superiority is additionally proved under stochastic system environments.

• 전자공학회논문지B
• /
• 제33B권2호
• /
• pp.159-167
• /
• 1996

In this paper, a new competitive learning algorithm called dynamic competitive learning (DCL) is presented. DCL is a supervised learning mehtod that dynamically generates output neuraons and nitializes weight vectors from training patterns. It introduces a new parameter called LOG (limit of garde) to decide whether or not an output neuron is created. In other words, if there exist some neurons in the province of LOG that classify the input vector correctly, then DCL adjusts the weight vector for the neuraon which has the minimum grade. Otherwise, it produces a new output neuron using the given input vector. It is largely learning is not limited only to the winner and the output neurons are dynamically generated int he trining process. In addition, the proposed algorithm has a small number of parameters. Which are easy to be determined and applied to the real problems. Experimental results for patterns recognition of remote sensing data and handwritten numeral data indicate the superiority of dCL in comparison to the conventional competitive learning methods.

• 아동학회지
• /
• 제23권1호
• /
• pp.55-70
• /
• 2002

The influence of peer collaboration on children's analogical abilities was studied with 120 9-year-old participants. After the pre-test, which determined the analogical level of the children, each child was assigned to 1 of 4 different learning conditions: cued/non-cued peer collaborative learning, or cued/non-cued individual learning conditions. The post-test showed changes in their analogical abilities. That is, results showed that cued peer collaborative learned improved the analogical abilities of the children, but the pattern of improvement was different by prior level of analogical abilities. We explained improvement in analogical ability by the context effect of peer collaborative learning and by the interactive effect of context with basic cognitive abilities of the children. We suggested implications of the present results for educational practice.

• International journal of advanced smart convergence
• /
• 제5권4호
• /
• pp.32-39
• /
• 2016

Machine learning is a field of artificial intelligence (AI), and a technology that collects, forecasts, and analyzes securities data is developed upon machine learning. The difference between using machine learning and not using machine learning is that machine learning-seems similar to big data-studies and collects data by itself which big data cannot do. Machine learning can be utilized, for example, to recognize a certain pattern of an object and find a criminal or a vehicle used in a crime. To achieve similar intelligent tasks, data must be more effectively collected than before. In this paper, we propose a method of effectively collecting data.

• 정보학연구
• /
• 제5권2호
• /
• pp.17-26
• /
• 2002

본 연구에서는 자기조직화 교사학습 신경망인 SOSL(Self-Organized Superised Learning)과 이 신경망의 구조를 제안한다. SOSL신경망은 하이브리드 형태의 신경망으로써 다수 개의 컴포넌트 에러 역전파 신경망들과 수정된 PCA신경망으로 구성된다. CBP신경망은 군집화되고 복잡한 입력패턴에 대하여 교사학습을 병렬적으로 수행한다. 수정된 PCA신경망은 군집화 및 지역투영에 의하여 원 입력패턴을 보다 작은 차원으로 변환시키기 위하여 사용된다. 제안된 SOSL은 많은 입력패턴을 가짐으로써 큰 네트워크 크기를 가지게 되는 신경망에 효과적으로 적용이 가능하다.

• 한국수학교육학회지시리즈A:수학교육
• /
• 제42권4호
• /
• pp.453-463
• /
• 2003

The main purpose of this paper is to develope elementary mathematics teaching-learning programs for pre-service elementary teachers. The elementary mathematics education program developed in this work is divided into two parts: One is the theory, the other is the practice. The theory deals with the foundations of mathematics, the objectives of mathematics education, the history of mathematics education in Korea, the psychology of mathematics learning, the theories of mathematics teaching and learning, and the methods of assessment. With respect to the practice, this study examines the background knowledge and activities of numbers and their operation, geometry, measurement, statistics and probability, pattern and function.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제11권2호
• /
• pp.84-88
• /
• 2011

In this paper, a new competition strategy for learning vector quantization is proposed. The simple competitive strategy used for learning vector quantization moves the winning prototype which is the closest to the newly given data pattern. We propose a new learning strategy based on k-nearest neighbor prototypes as the winning prototypes. The selection of several prototypes as the winning prototypes guarantees that the updating process occurs more frequently. The design is illustrated with the aid of numeric examples that provide a detailed insight into the performance of the proposed learning strategy.