• Journal of Electrical Engineering and information Science
• /
• 제1권1호
• /
• pp.108-117
• /
• 1996

In this paper, we propose a new type of recurrent neural network architecture in which each output unit is connected with itself and fully-connected with other output units and all hidden units. The proposed recurrent network differs from Jordan's and Elman's recurrent networks in view of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving the discrimination and generalization power. We also prove the convergence property of learning algorithm of the proposed recurrent neural network and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. Experimental results confirmed that the proposed recurrent neural network improves the discrimination and generalization power in recognizing spatial patterns.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 2005년도 ICCAS
• /
• pp.2521-2525
• /
• 2005

In this paper, we presented a predictive control technique, which is based on wavelet neural network (WNN), for the control of chaotic systems whose precise mathematical models are not available. The WNN is motivated by both the multilayer feedforward neural network definition and wavelet decomposition. The wavelet theory improves the convergence of neural network. In order to design predictive controller effectively, the WNN is used as the predictor whose parameters are tuned by error between the output of actual plant and the output of WNN. Also the training method for the finding a good WNN model is the Extended Kalman algorithm which updates network parameters to converge to the reference signal during a few iterations. The benefit of EKF training method is that the WNN model can have better accuracy for the unknown plant. Finally, through computer simulations, we confirmed the performance of the proposed control method.

• 전자공학회논문지B
• /
• 제32B권3호
• /
• pp.130-138
• /
• 1995

In this paper, a Novel Approach is Proposed which Identifies linear system Parameters Using a multilayer feedforward neural network trained with backpropagation algorithm. The parameters of linear system can be represented by x9t)/x(t) and x(t)/u(t). Thud, its parameters can be represented in terms of the derivative of output with respect to input of parameters can be represented in terms of the derivative of output with respect to input of trained neural network which is a function of weights and output of neurons. Mathematical representation of the proposed approach is derived, and its validity is shown by simulation results on 2-layer and 3-layer neural network.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제54권4호
• /
• pp.220-227
• /
• 2005

This paper presents hybrid artificial intelligent(HAI) controller based on the vector controlled IPMSM drive system. And it is based on artificial technologies that adaptive neural network fuzzy(A-NNF) is to speed control and artificial neural network(ANN) is to speed estimation. The salient feature of this technique is the HAI controller The hybrid action tolerates any inaccuracies in the fuzzy logic assignment rules or in the neural network stationary weights. Speed estimators using feedforward multilayer and artificial neural network(ANN) are compared. The back-propagation algorithm is easy to derived the estimated speed tracks precisely the actual motor speed. This paper presents the theoretical analysis as well as the simulation results to verify the effectiveness of the new hybrid intelligent control.

• 대한의용생체공학회:학술대회논문집
• /
• 대한의용생체공학회 1998년도 추계학술대회
• /
• pp.207-208
• /
• 1998

Classification of extracellularly recorded action potential into each unit is an important procedure for further analysis of spike trains as point process. We utilize feedforward neural network structures, multilayer perceptron and radial basis function network to implement spike classifier. For the efficient training of classifiers, nonlinear energy operator that can trace the instantaneous frequency as well as the amplitude of the input signal is used. Trained classifiers shows successful operation, up to 90% correct classification was possible under 1.2 of signal-to-noise ratio.

• 전산구조공학
• /
• 제10권2호
• /
• pp.265-272
• /
• 1997

본 논문은 신경망 근사 해석 모델 개발을 궁극적인 목적으로 하는 기초적 연구로서, 기존의 수치해석 알고리즘과의 성능 비교를 통하여 신경망 알고리즘의 특성과 역할을 수치해석의 관점에서 정확히 판단하는데 목적이 있다. 신경망 알고리즘을 변형하여 선형 연립 방정식의 해를 구하는 두가지 방법을 제안하였고, 회귀분석, 보간법과의 비교를 통하여 광범위한 근사자(universal approximator)로서의 역할을 보였다.

• 대한산업공학회지
• /
• 제27권3호
• /
• pp.305-314
• /
• 2001

In this paper, we construct an automatic evaluation system of psychological feeling for corporate identity (CI) symbol mark based on a fuzzy neural network technique. The system is modelled by trainable fuzzy inference rules with several input variables (qualitative and quantitative design components of CI symbol mark) and a single output variable (consumer's feeling). The back propagation learning algorithm, which is a conventional learning method of multilayer feedforward neural networks, is used for parameter identification of the fuzzy inference system. The learning ability to train data and the generalization ability to test data are evaluated for the proposed evaluation system by computer simulations.

• 한국지능시스템학회논문지
• /
• 제15권2호
• /
• pp.264-269
• /
• 2005

Advances in sensors, actuators, and computers and developments In information systems offer unprecedented opportunities to implement highly ambitious automation, control and decision strategies. There are also new challenges and demands for control and automation in modern industrial practices. There is a growing need for an active participation from the information systems in industrial, manufacturing and process industry environments because currently there are many control problems. This paper provides pattern recognition to the monitoring system for solvent manufacturing process and shows performance in real-time response with multiple input signals. Data is teamed by a multilayer feedforward network trained by error-backpropagation. The two kinds of test results show that the trained network has the ability to show the current system status with different input data sets.

• Journal of the Korean Data and Information Science Society
• /
• 제8권2호
• /
• pp.163-171
• /
• 1997

공학 분야에서 신경망에 대한 관심은 신호처리, 로보틱스, 컨트롤, 문자인식, 패턴인식 그리고 컴퓨터 그래픽 분야등에서 연구되고 있으며, 이들은 함수근사응용과 밀접한 관련이있다. 통계학 분야에서는 패턴인식의 판별분석, 주성분분석, 회귀분석 그리고 군집분석을 위한 신경망등에 대한 연구가 활발히 이루어지고 있다. 문자인식을 위한 다층 신경망을 학습시키기 위해 역전파 알고리즘이 널리 사용되고 있으나 이 알고리즘은 긴 훈련기간, 극소점 문제, 이상치(outlier)에 민감하다는 단점을 지니고 있다. 이상치에 민감한 일반적인 역전파 알고리즘의 단점을 극복하기 위해 이상치에 민감하지 않은 로버스트 알고리즘의 필요성이 대두되었다. 본 논문에서는 통계물리에서 자주 사용하는 방법을 이용하여 제안한 로버스트 역전파 알고리즘을 문자인식에 적용하여 일반적인 역전파 알고리즘의 문자인식 성능과 비교하였다.

• Journal of the Korean Data and Information Science Society
• /
• 제9권2호
• /
• pp.345-355
• /
• 1998

다층전방향 신경망을 학습시키기 위해 역전파 알고리즘이 널리 사용되고 있으나 이 알고리즘은 긴 훈련시간, 극소점 문제, 이상치에 민감하다는 단점을 가지고 있다. 한편 실제문제에서는 많은 경우에 자료에 과대오차와 이상치가 포함되게 된다. 따라서 과대 오차에 민감하지 않고, 이상치의 영향을 최소화시키는 로버스트 역전파 알고리즘의 필요성이 대두되었다. 본 논문에서는 기존의 두종류의 로버스트 역전파 알고리즘을 이론적으로 비교하고 비선형 회귀 함수추정과 문자인식과 같은 패턴인식 문제에 적용하여 실험결과를 분석한다. 그리고 향후 연구과제로 신경망 학습을 위해 베이지안 기법의 사용을 제안한다.