• 한국정보과학회:학술대회논문집
• /
• 한국정보과학회 2001년도 가을 학술발표논문집 Vol.28 No.2 (2)
• /
• pp.313-315
• /
• 2001

본 논문에서 소개하는 알고리즘을 은닉층의 뉴런의 수를 학습하는 동안 동적으로 변화시켜 역전파 알고리즘의 단점인 Local maxima를 탈출하고 또한 은닉층의 뉴런의 수를 결정하는 과정을 없애기 위해 연구되었다. 본 알고리즘의 성능을 평가하기 위해 두 가지 실험에 적용하였는데 첫번째는 Exclusive-OR 문제이고 두번째는 7$\times$8 한글 자음과 모음의 폰트 학습에 적용하였다. 이 실험의 결과로 네트웍이 local maxima에 빠져드는 확률이 줄어드는 것을 알 수 있었고 학습속도 또한 일반적인 역전파 알고리즘보다 빠른 것으로 증명되었다.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2002년도 하계학술대회 논문집 D
• /
• pp.2149-2151
• /
• 2002

In this paper, a novel speed estimation method of an induction motor using neural networks(NNs) is presented. The NN speed estimator is trained online by using the error backpropagation algorithm, and the training starts simultaneously with the induction motor working. The neural network based vector controller has the advantage of robustness against machine parameter variation. The simulation results using Matlab/Simulink verify the useful of the proposed method.

• 한국통신학회논문지
• /
• 제19권12호
• /
• pp.2418-2425
• /
• 1994

기울기를 따라가는 방식(gradient descent method)에 바탕을 둔 오류 역전파(EBP : Error Back Propagation) 방법이 가장 널리 사용되는 신경회로망의 학습 방법에서 문제가 되는 지역 최소값(local minima), 느린 학습 시간, 신경망 구조(structure), 그리고 초기의 연결 강도(interconnection weight) 등을 기존의 다층 신경 회로망에 지역적인 학습 능력을 가진 가우시안 포텔샵 네트워크(GPFN : Gaussian Potential Function Networks)를 병렬적으로 부가하여 해결함으로써 지역화된 오류 학습 패턴들이 나타내는 문제에 대하여 학습 성능을 향상시킬 수 잇는 새로운 학습 방법을 제시한다. 함수 근사화 문제에서 기존의 EBP 학습 방법과의 비교 실험으로 제안된 학습 방법이 보다 개선된 일반화 능력과 빠른 학습 속도를 가짐을 보여 그 효율성을 입증한다.

• 한국인터넷방송통신학회논문지
• /
• 제11권4호
• /
• pp.91-97
• /
• 2011

본 논문에서는 Mackey-Glass시계열의 예측에서 유전자알고리즘을 이용하는 구조적인 동정과 뉴로퍼지에 의한 파라미터 동정의 학습방법과 하이브리드 시스템을 제안하였다. 본 방법은 두 가지로 구성되었다. 하나는 입력공간에 대한 분할을 통하여 유전 알고리즘을 이용하여 퍼지 규칙베이스를 구축하고 다른 하나는 이 규칙베이스를 토대로 기울기 최하강법을 이용하여 제어규칙의 변수에 대한 파라미터 동정이다. 제안된 방법을 성능을 검증하기 위하여 입력의 패턴을 시간간격에 따라서 x(t-3), x(t-6)과 x(t-9)의 세 가지로 구성하였다. 많은 시뮬레이션을 통하여 유전알고리즘에 의한 구조적인 동정으로 인하여 학습초기에 오차가 작은 것을 알 수 있었다. 표2에서와 같이 성능을 확인 할 수 있었다.

• 전자공학회논문지B
• /
• 제32B권1호
• /
• pp.50-63
• /
• 1995

In this paper, we propose a face recognition method using a neuro-fuzzy algorithm. In the preprocessing step, we extract the face part from the background image by tracking face boundaries. Then based on the a priori knowledge of human faces we extract the features such as widths of eyes and mouth, and distances from eye to nose and nose to mouth. In the recognition step. We use a neuro-fuzzy algorithm that employs a fuzzy membership function and modified error backpropagation algorithm. The former absorbs the variation of feature values and the latter shows good learning efficiency. Computer simulation results with 20 persons show that the proposed method gives higher recognition rate than the conventional ones.

• 경영과정보연구
• /
• 제3권
• /
• pp.201-214
• /
• 1999

Adaptive correlator receiver with neural network based on complex multilayer perceptron is persented for suppressing interference of narrow-band of direct spread spectrum communication systems. Recursive least square algorithm with backpropagation error is used for fast convergence and better performance in adaptive correlator scheme. According to signal noise and transmission power, computer simulation results show that bit error ratio of adaptive correlator using neural network improved that of adative transversal filter of direct sequence spread spectrum considering of jamming and narrow-band interference. Bit error ratio of adaptive correlator with neural network is reduced about 10-1 than that of adaptive transversal filter where interference versus signal ratio is 5dB.

• 한국전기전자재료학회:학술대회논문집
• /
• 한국전기전자재료학회 2008년도 하계학술대회 논문집 Vol.9
• /
• pp.525-526
• /
• 2008

For measuring nonlinear Vehicle Modeling based on 7-Depth Sensor, the neural networks are proposed m adaptive and in realtime. The structure of it is similar to recurrent neural networks; a delayed output as the input and a delayed error between the output of plant and neural networks as a bias input. In addition, we compute the desired value of hidden layer by an optimal method instead of transfering desired values by backpropagation and each weights are updated by RLS(Recursive Least Square). Consequently, this neural networks are not sensitive to initial weights and a learning rate, and have a faster convergence rate than conventional neural networks. This new neural networks is Error Estimated Neural Networks. We can estimate nonlinear models in realtime by the proposed networks and control nonlinear models.

• Journal of the Korean Data and Information Science Society
• /
• 제23권5호
• /
• pp.1027-1035
• /
• 2012

This paper proposes a new Levenberg-Marquardt algorithm that is accelerated by adjusting a Jacobian matrix and a quasi-Hessian matrix. The proposed method partitions the Jacobian matrix into block matrices and employs the inverse of a partitioned matrix to find the inverse of the quasi-Hessian matrix. Our method can avoid expensive operations and save memory in calculating the inverse of the quasi-Hessian matrix. It can shorten the training time for fast convergence. In our results tested in a large application, we were able to save about 20% of the training time than other algorithms.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권1호
• /
• pp.68-75
• /
• 1999

Machine recognition of faces from still and video images is emerging as an active research area spanning several disciplines such as image processing, pattern recognition, computer vision and neural networks. In addition, human face identification has numerous applications such as human interface based systems and real-time video systems of surveillance and security. In this paper, we propose an algorithm that can identify a particular individual face. We consider human face identification system in color space, which hasn't often considered in conventional in conventional methods. In order to make the algorithm insensitive to luminance, we convert the conventional RGB coordinates into normalized CIE coordinates. The normalized-CIE-based facial images are KL-transformed. The transformed data are used as the input of multi-layered neural network and the network are trained using error-backpropagation methods. Finally, we verify the system performance of the proposed algorithm by experiments.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2003년도 학술대회 논문집 전문대학교육위원
• /
• pp.49-51
• /
• 2003

This paper presents a speed control system of induction motor using neural network. The speed control of induction motor was designed to NNC(Neural Network Controller) and NNE(Neural Network Estimator) used backpropagation, the NNE was constituted to be get an error value of output of an induction motor and conspire an input/output. NNC is controled to be made the error of reference speed and actual speed decrease, and in order to determine the weighting of NNC can be back propagated through the NNE, and it is adapted to the outside circumstances and system characters with learning ability.