• 수산해양교육연구
• /
• 제21권2호
• /
• pp.278-290
• /
• 2009

The purpose of this study is to investigate the relationship between learning skills and cognitive functions on elementary school students. In this study CAS and Learning Skills Test(LST) were administered with 3 to 6 grade, 60 students from 5 elementary schools. The data were analyzed according to Pearson's correlation and Stepwise Multiple Regression Analysis. The results are as follows. Firstly, girls and older students showed significantly higher ability than boys and younger students on the learning skills. And girls significantly outperformed boys on the planning function and attention function and on the simultaneous cognitive function was the other way round. Secondly, learning skills were explained 41% by two variables that the planning function and the successive function which are sub factors of the cognitive function. And then, planning and successive processing effected to self-management, attention and planning to test-taking skills, successive processing and attention to class-participation skills, and successive processing to information processing.

• 한국초등과학교육학회지:초등과학교육
• /
• 제33권1호
• /
• pp.140-161
• /
• 2014

The purpose of this study was to analyze 181 papers about brain-based learning appeared in domestic scientific journals from 1989 to May of 2012 and suggest application conditions in elementary science education. The results of this study summarizes as follows; First, learning activity suggested by brain-based learning study is mainly explained by working of brain function. Learning activity explained by brain-based learning study are divided into 'learning according to specialized brain function, learning according to brain function integration and learning beyond specialization and integration of hemispheres'. Second, it searched how increased knowledge of brain structure and function affects learning. Analysis from this point of view suggests that brain-based learning study affects learning in many ways especially emotion, creativity and learning motivation. Third, brain-based learning study suggests various possibilities of learning activity reflecting brain plasticity. Plasticity which is one of most important characteristics of brain supports the validity of learning activity as learning disorder treatment and explains the possibility of selective increment of brain function by leaning activity and the need of whole-brain approach to learning activity. Fourth, brain-based learning brought paradigm shifts in education field. It supports learning sophistication on the understanding of student's learning activity, guides learning method that reflects the characteristics of subject and demands reconstruction of curriculum. Fifth, there are many conditions to apply brain-based learning in elementary science education field, learning environment that fits brain-based learning, change of perspectives on teaching and learning of science educators and development of brain-based learning curriculum are needed.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제31권11호
• /
• pp.1431-1438
• /
• 2004

강화학습(reinforcement learning)은 온라인으로 환경(environment)과 상호작용 하는 과정을 통하여 목표를 이루기 위한 전략을 학습한다. 강화학습의 기본적인 알고리즘인 Q-learning의 학습 속도를 가속하기 위해서, 거대한 상태공간 문제(curse of dimensionality)를 해결할 수 있고 강화학습의 특성에 적합한 함수 근사 방법이 필요하다. 본 논문에서는 이러한 문제점들을 개선하기 위해서, 온라인 퍼지 클러스터링(online fuzzy clustering)을 기반으로 한 Fuzzy Q-Map을 제안한다. Fuzzy Q-Map은 온라인 학습이 가능하고 환경의 불확실성을 표현할 수 있는 강화학습에 적합한 함수근사방법이다. Fuzzy Q-Map을 마운틴 카 문제에 적용하여 보았고, 학습 초기에 학습 속도가 가속됨을 보였다.

• 전자공학회논문지B
• /
• 제29B권1호
• /
• pp.94-101
• /
• 1992

The multilayer perceptron, trained by the error back-propagation learning rule, has been known as a mapping network which can represent arbitrary functions. However depending on the complexity of a function and the initial weights of the multilayer perceptron, the error back-propagation learning may fall into a local minimum or a flat area which may require a long learning time or lead to unsuccessful learning. To solve such difficulties in training the multilayer perceptron by standard error back-propagation learning rule, the paper proposes a learning method which progressively enlarges the learning domain from a small area to the entire region. The proposed method is devised from the investigation on the roles of hidden nodes and connection weights in the multilayer perceptron which approximates a function of one variable. The validity of the proposed method was illustrated through simulations for a function of one variable and a function of two variable with many extremal points.

• Journal of Information Processing Systems
• /
• 제16권5호
• /
• pp.1074-1082
• /
• 2020

Recently, research has been actively conducted to create artificial intelligence agents that learn games through reinforcement learning. There are several factors that determine performance when the agent learns a game, but using any of the activation functions is also an important factor. This paper compares and evaluates which activation function gets the best results if the agent learns the game through reinforcement learning in the 2D racing game environment. We built the agent using a reinforcement learning algorithm and a neural network. We evaluated the activation functions in the network by switching them together. We measured the reward, the output of the advantage function, and the output of the loss function while training and testing. As a result of performance evaluation, we found out the best activation function for the agent to learn the game. The difference between the best and the worst was 35.4%.

• 제어로봇시스템학회논문지
• /
• 제3권6호
• /
• pp.594-601
• /
• 1997

A new algorithm is proposed for training the multilayer perceptrion(MLP) in pattern classification problems to accelerate the learning speed. It is shown that the sigmoid activation function of the output node can have deterimental effect on the performance of learning. To overcome this detrimental effect and to use the information fully in supervised learning, an objective function for binary modes is proposed. This objective function is composed with two new output activation functions which are selectively used depending on desired values of training patterns. The effect of the objective function is analyzed and a training algorithm is proposed based on this. Its performance is tested in several examples. Simulation results show that the performance of the proposed method is better than that of the conventional error back propagation (EBP) method.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.941-946
• /
• 2005

In this paper an active random noise control using adaptive learning rate neural networks is presented. The adaptive learning rate strategy increases the learning rate by a small constant if the current partial derivative of the objective function with respect to the weight and the exponential average of the previous derivatives have the same sign, otherwise the learning rate is decreased by a proportion of its value. The use of an adaptive learning rate attempts to keep the learning step size as large as possible without leading to oscillation. It is expected that a cost function minimize rapidly and training time is decreased. Numerical simulations and experiments of active random noise control with the transfer function of the error path will be performed, to validate the convergence properties of the adaptive learning rate Neural Networks. Control results show that adaptive learning rate Neural Networks control structure can outperform linear controllers and conventional neural network controller for the active random noise control.

• 한국정보통신설비학회:학술대회논문집
• /
• 한국정보통신설비학회 2009년도 정보통신설비 학술대회
• /
• pp.382-386
• /
• 2009

Online or sequential learning is one of the most basic and powerful method to train neuron network, and it has been widely used in disease detection, weather prediction and other realistic classification problem. At present, there are many algorithms in this area, such as MRAN, GAP-RBFN, OS-ELM, SVM and SMC-RBF. Among them, SMC-RBF has the best performance; it has less number of hidden neurons, and best efficiency. However, all the existing algorithms use signal normal distribution as kernel function, which means the output of the kernel function is same at the different direction. In this paper, we use multi-variable normal distribution as kernel function, and derive EKF learning formulas for multi-variable normal distribution kernel function. From the result of the experience, we can deduct that the proposed method has better efficiency performance, and not sensitive to the data sequence.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권1호
• /
• pp.1-15
• /
• 2023

The aim of this study is to identify intelligent learning support functions in Learning Management System (LMS) to support university student learning activities during the transition from face-to-face classes to online learning. To accomplish this, we investigated the perceptions of students on the levels of importance and urgency toward learning support functions of LMS powered with Artificial Intelligent (AI) technology and analyzed the differences in perception according to student characteristics. As a result of this study, the function that students considered to be the most important and felt an urgent need to adopt was to give automated grading and feedback for their writing assignments. The functions with the next highest score in importance and urgency were related to receiving customized feedback and help on task performance processed as well as results in the learning progress. In addition, students view a function to receive customized feedback according to their own learning plan and progress and to receive suggestions for improvement by diagnosing their strengths and weaknesses to be both vitally important and urgently needed. On the other hand, the learning support function of LMS, which was ranked as low importance and urgency, was a function that analyzed the interaction between professors and students and between fellow students. It is expected that the results of this student needs analysis will be helpful in deriving the contents of learning support functions that should be developed as well as providing basic information for prioritizing when applying AI technology to implement learner-centered LMS in the future.

• 전기전자학회논문지
• /
• 제25권4호
• /
• pp.728-734
• /
• 2021

최근 심층강화학습을 활용한 종단간 자율주행에 대한 관심이 크게 증가하고 있다. 본 논문에서는 차량의 종방향 주행 성능을 개선하는 잠재 SAC 기반 심층강화학습의 보상함수를 제시한다. 기존 강화학습 보상함수는 주행 안전성과 효율성이 크게 저하되는 반면 제시하는 보상함수는 전방 차량과의 충돌위험을 회피하면서 적절한 차간거리를 유지할 수 있음을 보인다.