• 전자공학회논문지B
• /
• 제29B권4호
• /
• pp.58-65
• /
• 1992

In this paper new back propagation algorithm which adds neurons to hidden layer is proposed. this proposed algorithm is applied to the pattern recognition of written number coupled with back propagation algorithm through omitting redundant learning. Learning rate and recognition rate of the proposed algorithm are compared with those of the conventional back propagation algorithm and the back propagation through omitting redundant learning. The learning rate of proposed algorithm is 4 times as fast as the conventional back propagation algorithm and 2 times as fast as the back propagation through omitting redundant learning. The recognition rate is 96.2% in case of the conventional back propagation algorithm, 96.5% in case of the back propagation through omitting redundant learning and 97.4% in the proposed algorithm.

• 한국농공학회지
• /
• 제36권2호
• /
• pp.88-95
• /
• 1994

This paper is to evaluate the applicability of neural networks to the estimation of evapotranspiration. Two neural networks were developed to forecast daily evapotranspiration of the rice crop with back-propagation and counter-propagation algorithm. The neural network trained by back-propagation algorithm with delta learning rule is a three-layer network with input, hidden, and output layers. The other network with counter-propagation algorithm is a four-layer network with input, normalizing, competitive, and output layers. Training neural networks was conducted using daily actual evapotranspiration of rice crop and daily climatic data such as mean temperature, sunshine hours, solar radiation, relative humidity, and pan evaporation. During the training, neural network parameters were calibrated. The trained networks were applied to a set of field data not used in the training. The created response of the back-propagation network was in good agreement with desired values and showed better performances than the counter-propagation network did. Evaluating the neural network performance indicates that the back-propagation neural network may be applied to the estimation of evapotranspiration of the rice crop. This study does not provide with a conclusive statement as to the ability of a neural network to evapotranspiration estimating. More detailed study is required for better understanding and evaluating the behavior of neural networks.

• 정보처리학회논문지B
• /
• 제9B권5호
• /
• pp.673-680
• /
• 2002

이 논문은 진화 프로그래밍과 개선된 역전파 알고리즘을 이용한 에지 검출 방법을 제안한다. 진화 프로그래밍은 알고리즘의 성능저하와 계산비용을 고려하여 교차 연산은 수행하지 않고, 선택연산자와 돌연변이 연산자를 사용한다. 개선된 역전파 알고리즘은 학습단계에서 연결강도를 변화시킬 때 이전학습단계의 연결강도를 보조적으로 활용하는 방법이다. 이 개선된 역전파 알고리즘은 학습률 $\alpha$를 작은값으로 설정하기 때문에 각 학습단계에서의 연결강도 변화량이 기존의 방법에 비해 상대적으로 줄어들게 되어 학습이 느려지는 문제점을 해결하였다. 실험결과 학습시간과 검출률에 있어서 GA-BP(GA : Genetic Algorithm BP : Back-Propagation)를 이용한 방법보다 제안한 EP-MBP(EP : Evolutionary Programming, MBP :Momentum Back-Propagation)를 이용하여 학습시킨 방법이 학습시간의 단축과 효율적인 에지 검출 결과를 얻을 수 있었다.

• 정보학연구
• /
• 제8권1호
• /
• pp.51-56
• /
• 2005

The Back propagation algorithm is a very effective supervised training method for multi-layer feed forward neural networks. This paper studies the decision boundary formation based on the Back propagation algorithm. The discriminating powers of several neural network topology are also investigated against five manually created data sets. It is found that neural networks with multiple hidden layer perform better than single hidden layer.

• Journal of information and communication convergence engineering
• /
• 제22권3호
• /
• pp.231-236
• /
• 2024

This paper presents a method used to identify partial discharge defects in cast-resin power transformers using a back-propagation algorithm. The Rogowski-type partial discharge (PD) sensor was designed with a planar and thin structure based on a printed circuit board to detect PD signals. PD electrode systems, such as metal protrusions, particle-on-insulators, delamination, and void defects, were fabricated to simulate the PD defects that occur in service. PD characteristics, such as rising time, falling time, pulse width, skewness, and kurtosis without phase-resolved partial discharge patterns, were extracted to intuitively analyze each PD pulse according to the type of PD defect. A backpropagation algorithm was designed to identify PD defects using a virtual instrument (VI) based on the LabVIEW program. The results show that the accuracy rate of back-propagation (BP) algorithm reaches over 92.75% in identifying four types of PD defects.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.442-445
• /
• 1997

We present a hybrid self-tuning method of fuzzy inference systems with hyper elliptic Gaussian membership functions using genetic algorithm(GA) and back-propagation algorithm. The proposed self-tuning method has two phases : one is the coarse tuning process based on GA and the other is the fine tuning process based on back-propagation. But the parameters which is obtained by a GA are near optimal solutions. In order to solve the problem in GA applications, it uses a back-propagation algorithm, which is one of learning algorithms in neural networks, to finely tune the parameters obtained by a GA. We provide Box-Jenkins time series to evaluate the advantage and effectiveness of the proposed approach and compare with the conventional method.

• 한국소성가공학회:학술대회논문집
• /
• 한국소성가공학회 2009년도 춘계학술대회 논문집
• /
• pp.357-360
• /
• 2009

The cooling stage greatly affects the product quality in the injection molding process. The cooling system that minimizes temperature variance in the product surface will improve the quality and the productivity of products. In this research, we tried the back-propagation algorithm of artificial neural network to find an optimum solution in the cooling system design of injection mold. The cooling system optimization problem that was once solved by a response surface method with 4 design variables was solved by applying the back-propagation algorithm, resulting in a solution with a sufficient accuracy. Furthermore the number of training points was much reduced by applying the fractional factorial design without losing solution accuracy.

• 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.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1999년도 하계학술대회 논문집 G
• /
• pp.2932-2934
• /
• 1999

In this paper, a scheme for recognition of handwritten digits using a multilayer neural network trained with the back-propagation algorithm using generalized delta rule is proposed. The neural network is trained with hand written digit data of different writers and different styles. One of the purpose of the work with neural networks is the minimization of the mean square error(MSE) between actual output and desired one. The back-propagation algorithm is an efficient and very classical method. The back-propagation algorithm for training the weights in a multilayer net uses the steepest descent minimization procedure and the sigmoid threshold function. As an error rate is reduced, recognition rate is improved. Therefore we propose a method that is reduced an error rate.

• 전자공학회논문지B
• /
• 제33B권9호
• /
• pp.49-61
• /
• 1996

Back-propagation(BP) algorithm needs a lot of time to train the artificial neural network (ANN) to get high accuracy level in classification tasks. So there have been extensive researches to process back-propagation algorithm on parallel processors. This paper prsents a linear systolic array which calculates forward-backward propagation of BP algorithm at the same time using effective space-time transformation and PE structure. First, we analyze data flow of forwared and backward propagations and then, represent the BP algorithm into data dapendency graph (DG) which shows parallelism inherent in the BP algorithm. Next, apply space-time transformation on the DG of ANN is turn with orthogonal direction projection. By doing so, we can get a snakelike systolic array. Also we calculate the interval of input for parallel processing, calculate the indices to make the right datas be used at the right PE when forward and bvackward propagations are processed in the same PE. And then verify the correctness of output when forward and backward propagations are executed at the same time. By doing so, the proposed system maximizes parallelism of BP algorithm, minimizes th enumber of PEs. And it reduces the execution time by 2 times through making idle PEs participate in forward-backward propagation at the same time.