• 대한한의학회지
• /
• 제40권1호
• /
• pp.78-85
• /
• 2019

Objectives:　The purpose of this study is to evaluate the development of the near poor Families' Children via learning disability indices, frontal executive function. Methods: Seventeen children (10 boys, 7 girls, 6.6-11.9 years) from the near poor Families' were enrolled in this study. Children were evaluated for a learning disability and frontal executive function. Results: In Learning disability indices, 3 children showed low scores in subscales and 2 children showed low scores in learning quotient. In Frontal executive function, 3 children showed low scores in CCTT (Children's Color Trails Test) and 11children showed low scores in STROOP (Stroop Color and Word Test). Conclusions: Intensive management, educational programs, and additional neuropsychological tests will be needed in children with low learning scores.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.72-74
• /
• 2021

다양한 분야에서 현재 활용되고 있는 딥러닝 과정은 데이터 준비, 데이터 전처리, 모델 생성, 모델 학습, 모델 평가로 구성 된다. 이중 모델 학습 과정에서 손실함수는 모델이 학습하면서 출력한 값을 실제 값과 비교하여 그 차이를 출력하게 되고, 출력된 손실값을 기반으로 모델은 역전파 알고리즘을 통해 손실값이 감소하는 방향으로 가중치를 수정해가며 학습을 진행한다. 본 논문에서는 바이오마커 추출을 위한 딥러닝 모델에서 사용될 신경망 출력 값의 손실도를 측정하여 출력해주는 다양한 손실함수를 분석하고 실험을 통해 최적의 손실함수를 찾아내고자 한다.

• 대한통합의학회지
• /
• 제9권1호
• /
• pp.13-22
• /
• 2021

Purpose : The purpose of this study was to investigate the effects of a virtual reality-based occupational therapy program on the physical function and learning ability of intellectually disabled school-aged children. Methods : In this study, 20 intellectually disabled children of school age were randomly and evenly divided into experimental and control groups with children in the experimental group receiving a virtual reality-based occupational therapy intervention. The study adopted a pretest-posttest design. The intervention was conducted for a total of 12 sessions for six weeks, twice a week, and 50 minutes per session. As measurement tools, BOT-2 and grooved pegboard tests were used to compare physical function before and after the intervention program, and K-ABC was used to check changes in learning ability. Results : The occupational therapy program produced a significant improvement in both physical function and learning ability of the experimental group. A significant difference was observed between the experimental and control groups. Conclusion : This study confirmed the value and usefulness of virtual reality-based occupational therapy as a tool for enhancing the physical function and learning ability of intellectually disabled school-aged children. Based on the results, a variety of future studies are encouraged that would further test the effects of the occupational therapy program used here.

• 한국지능시스템학회논문지
• /
• 제26권1호
• /
• pp.87-92
• /
• 2016

본 논문에서는 일반적인 신경회로망의 단점인 느린 학습속도를 획기적으로 개선한 네트워크인 Extreme Learning Machine과 전문가들의 언어적 정보들을 기술 할 수 있는 퍼지 이론을 접목한 퍼지 Extreme Learning Machine을 최적화하기 위하여 Particle Swarm Optimization 알고리즘을 이용하였다. 퍼지 Extreme Learning Machine의 활성화 함수를 일반적인 시그모이드 함수를 사용하지 않고, 퍼지 C-Means 클러스터링 알고리즘의 활성화 레벨 함수를 이용하였다. Particle Swarm Optimization 알고리즘과 같은 최적화 알고리즘을 통하여 퍼지 Extreme Learning Machine의 활성화 함수의 파라미터들을 최적화 한다. Particle Swarm Optimization과 같은 최적화 알고리즘을 통한 제안된 모델의 최적화 하고 최적화된 모델의 분류성능을 평가하기 위하여 다양한 머신 러닝 데이터 집합을 사용하여 평가한다.

• International Journal of Precision Engineering and Manufacturing
• /
• 제3권1호
• /
• pp.33-42
• /
• 2002

Recently, various experiments to apply reinforcement learning method to the self-learning intelligent control of continuous dynamic system have been reported in the machine learning related research community. The reports have produced mixed results of some successes and some failures, and show that the success of reinforcement learning method in application to the intelligent control of continuous control systems depends on the ability to combine proper function approximation method with temporal difference methods such as Q-learning and value iteration. One of the difficulties in using function approximation method in connection with temporal difference method is the absence of guarantee for the convergence of the algorithm. This paper provides a proof of convergence of a particular function approximation method based on \"barycentric interpolator\" which is known to be computationally more efficient than multilinear interpolation .

• 한국지능시스템학회논문지
• /
• 제13권6호
• /
• pp.635-642
• /
• 2003

강화학습은 제어, 스케쥴링 등 많은 응용분야에서 성공적인 학습 결과를 얻었다. 기본적인 강화학습 알고리즘인 Q-Learning, TD(λ), SARSA 등의 학습 속도의 개선과 기억장소 등의 문제를 해결하기 위해서 여러 함수 근사방법(function approximation methods)이 연구되었다. 대부분의 함수 근사 방법들은 가정을 통하여 강화학습의 일부 특성을 제거하고 사전지식과 사전처리가 필요하다. 예로 Fuzzy Q-Learning은 퍼지 변수를 정의하기 위한 사전 처리가 필요하고, 국소 최소 자승법은 훈련 예제집합을 이용한다. 본 논문에서는 온-라인 퍼지 클러스터링을 이용한 함수 근사 방법인 Fuzzy Q-Map을 제안하다. Fuzzy Q-Map은 사전 지식이 최소한으로 주어진 환경에서, 온라인으로 주어지는 상태를 거리에 따른 소속도(membership degree)를 이용하여 분류하고 행동을 예측한다. Fuzzy Q-Map과 다른 함수 근사 방법인 CMAC와 LWR을 마운틴 카 문제에 적용하여 실험 한 결과 Fuzzy Q-Map은 훈련예제를 사용하지 않는 CMAC보다는 빠르게 최고 예측율에 도달하였고, 훈련 예제를 사용한 LWR보다는 낮은 예측율을 보였다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2001년도 춘계학술대회 학술발표 논문집
• /
• pp.43-46
• /
• 2001

We, in this paper, design the Sugeno-models fuzzy controller by using the membership function modification algorithm and ANFIS, which are clustering and learning the input-output data. The membership function modification algorithm constructs the more concrete fuzzy controller by clustering the input-output data from the fuzzy inference system. ANFIS construct the Sugeno-models fuzzy controller by learning the input-output data from the above controller. We showed that the fuzzy controller designed by our method could have the stable learning and the enhanced performance.

• Journal of the Korean Data and Information Science Society
• /
• 제15권2호
• /
• pp.477-483
• /
• 2004

One of the major paradigms for supervised learning in neural network community is back-propagation learning. The standard implementations of back-propagation learning are optimal under the assumptions of identical and independent Gaussian noise. In this paper, for regression function estimation, we introduce $\varepsilon-insensitive$ back-propagation learning algorithm, which corresponds to minimizing the least absolute error. We compare this algorithm with support vector machine(SVM), which is another $\varepsilon-insensitive$ supervised learning algorithm and has been very successful in pattern recognition and function estimation problems. For comparison, we consider a more realistic model would allow the noise variance itself to depend on the input variables.

• Journal of Electrical Engineering and information Science
• /
• 제2권6호
• /
• pp.191-196
• /
• 1997

Fuzzy clustering has been playing an important role in solving many problems. Fuzzy c-Means(FCM) algorithm is most frequently used for fuzzy clustering. But some fixed point of FCM algorithm, know as Tucker's counter example, is not a reasonable solution. Moreover, FCM algorithm is impossible to perform the on-line learning since it is basically a batch learning scheme. This paper presents unsupervised learning networks as an attempt to improve shortcomings of the conventional clustering algorithm. This model integrates optimization function of FCM algorithm into unsupervised learning networks. The learning rule of the proposed scheme is a result of formal derivation based on the gradient descent procedure of a fuzzy objective function. Using the result of formal derivation, two algorithms of fuzzy cluster analysis, the batch learning version and on-line learning version, are devised. They are tested on several data sets and compared with FCM. The experimental results show that the proposed algorithms find out the reasonable solution on Tucker's counter example.

• ETRI Journal
• /
• 제17권1호
• /
• pp.11-22
• /
• 1995

This paper proposes a modified error function to improve the error back-propagation (EBP) algorithm for multi-Layer perceptrons (MLPs) which suffers from slow learning speed. It can also suppress over-specialization for training patterns that occurs in an algorithm based on a cross-entropy cost function which markedly reduces learning time. In the similar way as the cross-entropy function, our new function accelerates the learning speed of the EBP algorithm by allowing the output node of the MLP to generate a strong error signal when the output node is far from the desired value. Moreover, it prevents the overspecialization of learning for training patterns by letting the output node, whose value is close to the desired value, generate a weak error signal. In a simulation study to classify handwritten digits in the CEDAR [1] database, the proposed method attained 100% correct classification for the training patterns after only 50 sweeps of learning, while the original EBP attained only 98.8% after 500 sweeps. Also, our method shows mean-squared error of 0.627 for the test patterns, which is superior to the error 0.667 in the cross-entropy method. These results demonstrate that our new method excels others in learning speed as well as in generalization.