• 한국인공지능학회지
• /
• 제5권1호
• /
• pp.1-9
• /
• 2017

Recently, the Q-Learning algorithm, which is one kind of reinforcement learning, is mainly used to implement artificial intelligence system in combination with deep learning. Many research is going on to improve the performance of Q-Learning. Therefore, purpose of theory try to improve the performance of Q-Learning algorithm. This Theory apply Cross Entropy Error to the loss function of Q-Learning algorithm. Since the mean squared error used in Q-Learning is difficult to measure the exact error rate, the Cross Entropy Error, known to be highly accurate, is applied to the loss function. Experimental results show that the success rate of the Mean Squared Error used in the existing reinforcement learning was about 12% and the Cross Entropy Error used in the deep learning was about 36%. The success rate was shown.

• International Journal of Contents
• /
• 제11권2호
• /
• pp.57-62
• /
• 2015

Relative entropy is a divergence measure between two probability density functions of a random variable. Assuming that the random variable has only two alphabets, the relative entropy becomes a cross-entropy error function that can accelerate training convergence of multi-layer perceptron neural networks. Also, the n-th order extension of cross-entropy (nCE) error function exhibits an improved performance in viewpoints of learning convergence and generalization capability. In this paper, we derive a new divergence measure between two probability density functions from the nCE error function. And the new divergence measure is compared with the relative entropy through the use of three-dimensional plots.

• ETRI Journal
• /
• 제17권1호
• /
• pp.11-22
• /
• 1995

This paper proposes a modified error function to improve the error back-propagation (EBP) algorithm for multi-Layer perceptrons (MLPs) which suffers from slow learning speed. It can also suppress over-specialization for training patterns that occurs in an algorithm based on a cross-entropy cost function which markedly reduces learning time. In the similar way as the cross-entropy function, our new function accelerates the learning speed of the EBP algorithm by allowing the output node of the MLP to generate a strong error signal when the output node is far from the desired value. Moreover, it prevents the overspecialization of learning for training patterns by letting the output node, whose value is close to the desired value, generate a weak error signal. In a simulation study to classify handwritten digits in the CEDAR [1] database, the proposed method attained 100% correct classification for the training patterns after only 50 sweeps of learning, while the original EBP attained only 98.8% after 500 sweeps. Also, our method shows mean-squared error of 0.627 for the test patterns, which is superior to the error 0.667 in the cross-entropy method. These results demonstrate that our new method excels others in learning speed as well as in generalization.

• 한국어정보학회:학술대회논문집
• /
• 한국어정보학회 2017년도 제29회 한글및한국어정보처리학술대회
• /
• pp.56-59
• /
• 2017

CNN(Convolutional Neural Network)을 이용하여 발화 주제 다중 분류 task를 multi-labeling 방법과, cluster 방법을 이용하여 수행하고, 각 방법론에 MSE(Mean Square Error), softmax cross-entropy, sigmoid cross-entropy를 적용하여 성능을 평가하였다. Network는 음절 단위로 tokenize하고, 품사정보를 각 token의 추가한 sequence와, Naver DB를 통하여 얻은 named entity 정보를 입력으로 사용한다. 실험결과 cluster 방법으로 문제를 변형하고, sigmoid를 output layer의 activation function으로 사용하고 cross entropy cost function을 이용하여 network를 학습시켰을 때 F1 0.9873으로 가장 좋은 성능을 보였다.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2008년도 춘계학술대회 논문집
• /
• pp.158-163
• /
• 2008

In inverse synthetic aperture radar (ISAR) imaging, An ISAR autofocusing algorithm is essential to obtain well-focused ISAR images. Traditional methods have relied on the approximation that the phase error due to target motion is a function of the cross-range dimension only. However, in the stepped-frequency radar system, it tends to become a two-dimensional function of both down-range and cross-range, especially when target's movement is very fast and the pulse repetition frequency (PRF) is low. In order to remove the phase error along down-range, this paper proposes a method called SAEM (subarray averaging and entropy minimization) [1] that uses a subarray averaging concept in conjunction with the entropy cost function in order to find target motion parameters, and a novel 2-D optimization technique with the inherent properties of the proposed entropy-based cost function. A well-focused ISAR image can be obtained from the combination of the proposed method and a traditional autofocus algorithm that removes the phase error along the cross-range dimension. The effectiveness of this method is illustrated and analyzed with simulated targets comprised of point scatters.

• 한국정보통신학회논문지
• /
• 제7권5호
• /
• pp.1044-1051
• /
• 2003

본 논문은 MLP의 학습 방법으로 사용되는 EBP학습, Cross Entropy함수, 계층별 학습을 소개하고, 필기체 숫자인식 문제를 대상으로 각 학습 방법의 장단점을 비교한다. 실험 결과, EBP학습은 학습 초기에 학습 속도가 다른 학습 방법에 비해 느리지만, 일반화 성능이 좋다. 또한, EBP학습의 단점을 보안한 Cross Entropy 함수는 학습 속도가 EBP학습보다 빠르다. 그러나, 출력층의 오차 신호가 목표 벡터에 대해 선형적으로 학습하기 때문에, 일반화 성능이 EBP학습보다 낮다. 그리고, 계층별 학습은 학습 초기에, 학습 속도가 가장 빠르다. 그러나, 일정한 시간 후, 더 이상 학습이 진행되지 않기 때문에, 일반화 성능이 가장 낮은 결과를 얻었다. 따라서, 본 논문은 MLP를 응용하고자 할 때, 학습 방법의 선택 기준을 제시한다.

• International Journal of Contents
• /
• 제8권4호
• /
• pp.30-35
• /
• 2012

Error surfaces provide us with very important information for training of feed-forward neural networks (FNNs). In this paper, we draw the contour plots of various error or objective functions for training of FNNs. Firstly, when applying FNNs to classifications, the weakness of mean-squared error is explained with the viewpoint of error contour plot. And the classification figure of merit, mean log-square error, cross-entropy error, and n-th order extension of cross-entropy error objective functions are considered for the contour plots. Also, the recently proposed target node method is explained with the viewpoint of contour plot. Based on the contour plots, we can explain characteristics of various error or objective functions when training of FNNs proceeds.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권12호
• /
• pp.3889-3903
• /
• 2022

To address the problem of low detection accuracy due to training noise caused by mislabeling when Tri-training for network intrusion detection (NID), we propose a Tri-training algorithm based on cross entropy and K-nearest neighbors (TCK) for network intrusion detection. The proposed algorithm uses cross-entropy to replace the classification error rate to better identify the difference between the practical and predicted distributions of the model and reduce the prediction bias of mislabeled data to unlabeled data; K-nearest neighbors are used to remove the mislabeled data and reduce the number of mislabeled data. In order to verify the effectiveness of the algorithm proposed in this paper, experiments were conducted on 12 UCI datasets and NSL-KDD network intrusion datasets, and four indexes including accuracy, recall, F-measure and precision were used for comparison. The experimental results revealed that the TCK has superior performance than the conventional Tri-training algorithms and the Tri-training algorithms using only cross-entropy or K-nearest neighbor strategy.

• International Journal of Contents
• /
• 제10권1호
• /
• pp.23-28
• /
• 2014

When developing a classifier using various objective functions, it is important to compare the performances of the classifiers. Although there are statistical analyses of objective functions for classifiers, simulation results can provide us with direct comparison results and in this case, a comparison criterion is considerably critical. A Receiver Operating Characteristics (ROC) graph is a simulation technique for comparing classifiers and selecting a better one based on a performance. In this paper, we adopt the ROC graph to compare classifiers trained by mean-squared error, cross-entropy error, classification figure of merit, and the n-th order extension of cross-entropy error functions. After the training of feed-forward neural networks using the CEDAR database, the ROC graphs are plotted to help us identify which objective function is better.

• 한국정보과학회 언어공학연구회:학술대회논문집(한글 및 한국어 정보처리)
• /
• 한국정보과학회언어공학연구회 2017년도 제29회 한글 및 한국어 정보처리 학술대회
• /
• pp.56-59
• /
• 2017

CNN(Convolutional Neural Network)을 이용하여 발화 주제 다중 분류 task를 multi-labeling 방법과, cluster 방법을 이용하여 수행하고, 각 방법론에 MSE(Mean Square Error), softmax cross-entropy, sigmoid cross-entropy를 적용하여 성능을 평가하였다. Network는 음절 단위로 tokenize하고, 품사정보를 각 token의 추가한 sequence와, Naver DB를 통하여 얻은 named entity 정보를 입력으로 사용한다. 실험결과 cluster 방법으로 문제를 변형하고, sigmoid를 output layer의 activation function으로 사용하고 cross entropy cost function을 이용하여 network를 학습시켰을 때 F1 0.9873으로 가장 좋은 성능을 보였다.