• Journal of Biosystems Engineering
• /
• v.15 no.3
• /
• pp.186-198
• /
• 1990

인간 소뇌의 구조와 기능을 간략하게 수학적으로 모델링하여 입력에 따른 시스템의 적정 출력을 학습에 의한 적응 제어 방식으로 추출해 내는 소뇌모델 대수제어기(CMAC : Cerebellar Model Arithmetic Controller)가 제안되었다. 본 논문에서는 연구개발된 기존 신경회로망과의 비교 분석에 의거하여, 소뇌모델 대수제어기 대신 네트의 특성에 따라 소뇌모델 선형조합 신경망(CMLAN : Cerebellum Model Linear Associator Network)이라 하였다. 소뇌모델 선형조합 신경망은 시스템의 제어 함수치를 결정하는 데 있어, 기존의 제어방식이 시스템의 모델링을 기초로 하여 알고리즘에 의한 수치해석적 또는 분석적 기법으로 모델 해를 산출하는 것과 달리, 학습을 통하여 저장되는 분산기억 소자들의 함수치를 선형적으로 조합함으로써 시스템의 입출력을 결정한다. 분산기억 소자로의 함수치 산정 및 저장은 소뇌모델 선형조합 신경망이 갖는 고유의 구조적 상태공간 매핑(State Space Mapping)과 델타규칙(Delta Rule)에 의거한 시스템의 입출력 상태함수의 학습으로써 수행된다. 본 논문을 통하여 소뇌모델 선형조합신경망의 구조적 특성, 학습 성질과 상태공간 설정 및 시스템의 수렴성을 규명하였다. 또한 기존의 최대 편차수정 학습 알고리즘이 갖는 비능률성 및 적용 제한성을 극복한 효율적 학습 알고리즘들을 제시하였다. 언급한 신경망의 특성 및 제안된 학습 알고리즘들의 능률성을 다양한 학습이득(Learning Gain)하에서 비선형 함수를 컴퓨터로 모의 시험하여 예시하였다.

• Proceedings of the IEEK Conference
• /
• 2005.11a
• /
• pp.667-670
• /
• 2005

본 논문은 100um와 80um의 텅스텐 와이어를 이용하여 세라믹(Ceramic)기판에 홀(Hole)을 뚫어 텅스텐 와이어를 수직으로 세우는 방식으로 수직형의 마이크로 스프링을 제작하였다. 마이크로 스프링의 설계를 위해 제한된 실험 결과와 신경회로망을 이용하여 텅스텐 와이어의 두께와 높이, 쉬프트(Shift)의 양을 변화시키면서 장력(Tension force)을 모델링하였고 제작을 통해 검증하였다. 이는 기존의 수평형 프로브카드의 한계를 대체할 수 있는 수직형 프로브카드의 핵심 모듈로서 멀티다이(Multi Die) 뿐만 아니라 범핑(Bumping)타입의 칩 테스트도 가능하다.

• 제어로봇시스템학회:학술대회논문집
• /
• 1992.10a
• /
• pp.619-623
• /
• 1992

In pattern recognition, the conventional neural networks contain a large number of weights and require considerable training times and preprocessor to classify a transformed patterns. In this paper, we propose a constrained pattern recognition method which is insensitive to rotation of input pattern by various degrees and does not need any preprocessing. Because these neural networks can not be trained by the conventional training algorithm such as error back propagation, a novel training algorithm is suggested. As such a system is useful in problem related to calssify overse side and reverse side of 500 won coin. As an illustrative example, identification problem of overse and reverse side of 500 won coin is shown.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2005.05a
• /
• pp.431-434
• /
• 2005

근원데이터나, 이원데이터를 이용한 문제를 해결하기 위해서는 많은 경우에 완전 해를 갖는 문제로 변형시키기 위해 정규화할 필요성이 있다. 본 논문에서는 이러한 정규화 인수를 찾는 문제를 기존의 GCV, L-Curve, 그리고 이원데이터를 RBF 신경회로망에 적용시킨 커널 학습법에 대한 각각의 성능을 비교실험을 통해 고찰한다. 이때 커널을 이용한 학습법의 성능을 향상하기 위해, 전체학습과 성능의 제한적 비례관계라는 설정아래, 각각의 학습에 따라 능동적으로 변화하는 동적모멘텀의 도입을 제안한다. 끝으로 제안된 동적모멘텀이 분류문제의 표준인 Iris 데이터, Singular 시스템의 대표적 모델인 가우시안 데이터, 그리고 마지막으로 1차원 이미지 복구문제인 Shaw데이터를 이용한 각각의 실험에서 분류문제와 회계문제 양쪽 모두에 있어 기존의 GCV, L-Curve와 동등하거나 우수한 성능이 있음을 보인다.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 1999.05a
• /
• pp.370-374
• /
• 1999

The proposed algorithm used the Hybrid teaming rule in the input and hidden layer, and Back-Propagation teaming rule in the hidden and output layer. From the results of simulation of tracking control with one link manipulator as a plant, we verify the usefulness of the proposed control method to compare with common direct adaptive neural network control method; proposed hybrid teaming rule showed faster loaming time faster settling time than the direct adaptive neural network using Back-propagation algorithm. Usefulness of the proposed control method is that it is faster the learning time and settling time than common direct adaptive neural network control method.

• Journal of the Korean Society for Aeronautical & Space Sciences
• /
• v.37 no.3
• /
• pp.248-254
• /
• 2009

The use of evolutionary algorithm is limited in the field of aerodynamics, mainly because the population-based search algorithm requires excessive CPU time. In this paper a coupling method with adaptive range genetic algorithm for floating point and back-propagation neural network is proposed to efficiently obtain a converged solution. As a result, it is shown that a reduction of 14% and 33% respectively in wave drag and its consumed time can be achieved by the new method.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.18 no.10
• /
• pp.1422-1432
• /
• 1993

Nonlinear mapping function of the HCNN( Hidden Control Neural Network ) can change over time to model the temporal variability of a speech signal by combining the nonlinear prediction of conventional neural networks with the segmentation capability of HMM. We have two things in this paper. first, we showed that the performance of the HCNN is better than that of HMM. Second, the HCNN with its prediction error measure given by weighted distance is proposed to use suitable distance measure for the HCNN, and then we showed that the superiority of the proposed system for speaker-independent speech recognition tasks. Weighted distance considers the differences between the variances of each component of the feature vector extraced from the speech data. Speaker-independent Korean digit recognition experiment showed that the recognition rate of 95%was obtained for the HCNN with Euclidean distance. This result is 1.28% higher than HMM, and shows that the HCNN which models the dynamical system is superior to HMM which is based on the statistical restrictions. And we obtained 97.35% for the HCNN with weighted distance, which is 2.35% better than the HCNN with Euclidean distance. The reason why the HCNN with weighted distance shows better performance is as follows : it reduces the variations of the recognition error rate over different speakers by increasing the recognition rate for the speakers who have many misclassified utterances. So we can conclude that the HCNN with weighted distance is more suit-able for speaker-independent speech recognition tasks.

• Journal of KIISE:Software and Applications
• /
• v.32 no.11
• /
• pp.1021-1028
• /
• 2005

The general solution for classification and regression problems can be found by matching and modifying matrices with the information in real world and then these matrices are teaming in neural networks. This paper treats primary space as a real world, and dual space that Primary space matches matrices using kernel. In practical study, there are two kinds of problems, complete system which can get an answer using inverse matrix and ill-posed system or singular system which cannot get an answer directly from inverse of the given matrix. Further more the problems are often given by the latter condition; therefore, it is necessary to find regularization parameter to change ill-posed or singular problems into complete system. This paper compares each performance under both classification and regression problems among GCV, L-Curve, which are well known for getting regularization parameter, and kernel methods. Both GCV and L-Curve have excellent performance to get regularization parameters, and the performances are similar although they show little bit different results from the different condition of problems. However, these methods are two-step solution because both have to calculate the regularization parameters to solve given problems, and then those problems can be applied to other solving methods. Compared with UV and L-Curve, kernel methods are one-step solution which is simultaneously teaming a regularization parameter within the teaming process of pattern weights. This paper also suggests dynamic momentum which is leaning under the limited proportional condition between learning epoch and the performance of given problems to increase performance and precision for regularization. Finally, this paper shows the results that suggested solution can get better or equivalent results compared with GCV and L-Curve through the experiments using Iris data which are used to consider standard data in classification, Gaussian data which are typical data for singular system, and Shaw data which is an one-dimension image restoration problems.

• Journal of Digital Contents Society
• /
• v.17 no.3
• /
• pp.157-164
• /
• 2016

Solar power generation influenced by the weather. Using the weather forecast information, it is possible to predict the short-term solar power generation in the future. However, in limited circumstances such as islands or mountains, it can not be use weather forecast information by the disconnection of the network, it is impossible to use solar power generation prediction model using weather forecast. Therefore, in this paper, we propose a system that can predict the short-term solar power generation by using the information that can be collected by the system itself. We developed a short-term prediction model using the prior information of temperature and power generation amount to improve the accuracy of the prediction. We showed the usefulness of proposed prediction model by applying to actual solar power generation data.

• Journal of the Korean Institute of Telematics and Electronics S
• /
• v.36S no.2
• /
• pp.28-37
• /
• 1999

Differentially Responsible Adaptive Critic Learning technique is proposed for learning the control technique with multiple control inputs as in robot system using reinforcement learning. The reinforcement learning is a self-learning technique which learns the control skill based on the critic information Learning is a after a long series of control actions. The Adaptive Critic Learning (ACL) is the representative reinforcement learning structure. The ACL maximizes the learning performance using the two learning modules called the action and the critic modules which exploit the external critic value obtained seldomly. Drawback of the ACL is the fact that application of the ACL is limited to the single input system. In the proposed Differentially Responsible Action Dependant Adaptive Critic learning structure, the critic function is constructed as a function of control input elements. The responsibility of the individual control action element is computed based on the partial derivative of the critic function in terms of each control action element. The proposed learning structure has been constructed with the CMAC neural networks and some simulations have been done upon the two dimensional Cart-Role system and robot squatting problem. The simulation results are included.