• ETRI Journal
• /
• v.22 no.3
• /
• pp.10-18
• /
• 2000

Although an n-th order cross-entropy (nCE) error function resolves the incorrect saturation problem of conventional error backpropagation (EBP) algorithm, performance of multilayer perceptrons (MLPs) trained using the nCE function depends heavily on the order of nCE. In this paper, we propose an adaptive learning rate to markedly reduce the sensitivity of MLP performance to the order of nCE. Additionally, we propose to limit error signal values at out-put nodes for stable learning with the adaptive learning rate. Through simulations of handwritten digit recognition and isolated-word recognition tasks, it was verified that the proposed method successfully reduced the performance dependency of MLPs on the nCE order while maintaining advantages of the nCE function.

• International Journal of Contents
• /
• v.7 no.3
• /
• pp.1-5
• /
• 2011

It has been an interesting challenge to find a good classifier for imbalanced data, since it is pervasive but a difficult problem to solve. However, classifiers developed with the assumption of well-balanced class distributions show poor classification performance for the imbalanced data. Among many approaches to the imbalanced data problems, the algorithmic level approach is attractive because it can be applied to the other approaches such as data level or ensemble approaches. Especially, the error back-propagation algorithm using the target node method, which can change the amount of weight-updating with regards to the target node of each class, attains good performances in the imbalanced data problems. In this paper, we analyze the relationship between two optimal outputs of neural network classifier trained with the target node method. Also, the optimal relationship is compared with those of the other error function methods such as mean-squared error and the n-th order extension of cross-entropy error. The analyses are verified through simulations on a thyroid data set.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.73-74
• /
• 2021

코로나로 인해 X-ray, CT, MRI와 같은 의료영상 분야에서 딥러닝을 많이 접목시키고 있다. 간단히 접할 수 있는 X-ray 영상으로 코로나 진단을 위해 CNN, R-CNN 등과 같은 영상 딥러닝 분야에서 많은 연구가 진행되고 있다. 의료영상 기반 딥러닝 학습은 바이오마커를 정확히 찾아내고, 최소한의 손실률과 높은 정확도를 필요로한다, 따라서 본 논문에서는 높은 정확도를 위한 학습 모델을 선정하고 실험을 진행하였다.

• Journal of Digital Convergence
• /
• v.20 no.4
• /
• pp.389-396
• /
• 2022

Deep Learning is based on a perceptron, and is currently being used in various fields such as image recognition, voice recognition, object detection, and drug development. Accordingly, a variety of learning algorithms have been proposed, and the number of neurons constituting a neural network varies greatly among researchers. This study analyzed the learning characteristics according to the number of neurons of the currently used SGD, momentum methods, AdaGrad, RMSProp, and Adam methods. To this end, a neural network was constructed with one input layer, three hidden layers, and one output layer. ReLU was applied to the activation function, cross entropy error (CEE) was applied to the loss function, and MNIST was used for the experimental dataset. As a result, it was concluded that the number of neurons 100-300, the algorithm Adam, and the number of learning (iteraction) 200 would be the most efficient in deep learning learning. This study will provide implications for the algorithm to be developed and the reference value of the number of neurons given new learning data in the future.

• Korean Journal of Artificial Intelligence
• /
• v.5 no.1
• /
• pp.29-37
• /
• 2017

The range of problems that can be handled by the activation of big data and the development of hardware has been rapidly expanded and machine learning such as deep learning has become a very versatile technology. In this paper, mnist data set is used as experimental data, and the Cross Entropy function is used as a loss model for evaluating the efficiency of machine learning, and the value of the loss function in the steepest descent method is We applied the Gradient Descent Optimize algorithm to minimize and updated weight and bias via backpropagation. In this way we analyze optimal reliability value corresponding to the number of exercises and optimal reliability value without overfitting. And comparing the overfitting time according to the number of data changes based on the number of training times, when the training frequency was 1110 times, we obtained the result of 92%, which is the optimal reliability value without overfitting.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2017.04a
• /
• pp.881-884
• /
• 2017

좋은 특징을 도출할 수 있는 신경망은 곧 대상을 잘 이해하고 있는 신경망을 의미한다. 그러나 얼굴과 같이 유사한 이미지를 분류하기 위해서는 신경망이 좀 더 구분되는 특징을 도출해야한다. 본 논문에서는 얼굴과 같이 유사도한 이미지를 분류하기 위해 오차함수에 중심확장(Center Expansion)이라는 오차를 추가한다. 중심확장은 도출된 특징이 밀집되면 클래스를 분류하는 매니폴드를 구하기 어려워져 분류 성능이 하락되는 문제를 해결하기 위해 제안한 것으로 특징이 밀집될 가능성이 높은 부분에 특징이 도출되지 않도록 강제하는 방식이다. 학습 시 활용하는 오차는 일반적으로 분류 문제를 위해 사용되는 softmax cross-entropy 오차와 각 클래스의 분산을 줄이는 오차 그리고 제안한 중심확장 오차를 조합해 구할 것이다. 본 논문에서는 제안한 중심확장 오차를 조합한 모델과 조합되지 않은 모델이 결과적으로 특징 도출과 분류에 어떠한 영향을 주었는지 알아볼 것이다. 중심확장을 조합해 학습한 모델이 어떤 영향을 주었는지 알기 위해 본 논문에서는 Labeled Faces in the Wild를 활용해 분류 실험을 진행할 것이다. Labeled Faces in the Wild을 활용해 실험한 결과 중심확장을 활용한 모델과 활용하지 않은 모델간의 성능을 차이를 확인할 수 있었다.

• The Journal of the Korea Contents Association
• /
• v.11 no.4
• /
• pp.51-56
• /
• 2011

This paper proposes an efficient moving picture compression for video sequences with luminance variations. In the proposed algorithm, the luminance variation parameters are estimated and local motions are compensated. To detect the frame required luminance compensation, we employ the frame classification based on the cross entropy between histograms of two successive frames, which can reduce the computational redundancy. Simulation results show that the proposed method yields a higher peak signal to noise ratio (PSNR) than that of the conventional methods, with a low computational load, when the video scene contains large luminance variations.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.41 no.4
• /
• pp.11-16
• /
• 2004

A simple stopping criterion for iterative decoding based on min-sum processing is presented. While most stopping criteria suggested in the literature, are based on Cross Entropy (CE) and its simplification, the proposed stopping criterion is to check if a decoded sequence is a valid codeword along the encoder trellis structure. This new stopping criterion requires less computational complexity and saves mem4)ry compared to the conventional stopping rules. The numerical results are presented on the 3GPP turbo code and a Serially Concatenated Convolutional Cods (SCCC).

• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.55 no.3
• /
• pp.131-137
• /
• 2006

The secondary system of nuclear power plants consists of sophisticated piping systems operating in very aggressive erosion and corrosion environments, which make a piping system vulnerable to the wear and degradation due to the several chemical components and high flow rate (~10 m/sec) of the coolant. To monitor the wear and degradation on a pipe, the vibration signals are measured from the pipe with an accelerometer For analyzing the vibration signal the time-frequency analysis (TFA) is used, which is known to be effective for the analysis of time-varying or transient signals. To reduce the inteferences (cross-terms) due to the bilinear structure of the time-frequency distribution, an adaptive cone-kernel distribution (ACKD) is proposed. The cone length of ACKD to determine the characteristics of distribution is optimally selected through an adaptive algorithm using the normalized Shannon's entropy And the ACKD's are compared with the results of other analyses based on the Fourier Transform (FT) and other TFA's. The ACKD shows a better signature for the wear/degradation within a pipe and provides the additional information in relation to the time that any analysis based on the conventional FT can not provide.

• Journal of Korea Multimedia Society
• /
• v.21 no.12
• /
• pp.1425-1430
• /
• 2018

In this paper, we propose a CNN based deep learning algorithm for semantic segmentation of images. In order to improve the accuracy of semantic segmentation, we combined pixel level object classification and image level object classification. The image level object classification is used to accurately detect the characteristics of an image, and the pixel level object classification is used to indicate which object area is included in each pixel. The proposed network structure consists of three parts in total. A part for extracting the features of the image, a part for outputting the final result in the resolution size of the original image, and a part for performing the image level object classification. Loss functions exist for image level and pixel level classification, respectively. Image-level object classification uses KL-Divergence and pixel level object classification uses cross-entropy. In addition, it combines the layer of the resolution of the network extracting the features and the network of the resolution to secure the position information of the lost feature and the information of the boundary of the object due to the pooling operation.