• ETRI Journal
• /
• 제22권3호
• /
• 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.

• 한국해양공학회지
• /
• 제11권1호
• /
• pp.84-95
• /
• 1997

This paper presents a new approach to the design speed and azimuth control of a mobile robot with drive wheel. The proposed control scheme uses a Gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the frmework of the specialized learning architecture. It is proposed a learning controller consisting of two neural network-fuzzy based on independent reasoning and a connection net with fixed weights to simple the neural networks-fuzzy. The performance of the proposed controller is shown by performing the computer simulation for trajectory tracking of the speed and azimuth of a mobile robot driven by two independent wheels.

• 대한전기학회논문지:시스템및제어부문D
• /
• 제53권7호
• /
• pp.517-524
• /
• 2004

For real world applications of reinforcement learning techniques, function approximation or generalization will be required to avoid curse of dimensionality. For this, an improved function approximation-based reinforcement teaming method is proposed to speed up convergence by using CA-CMAC(Credit-Assigned Cerebellar Model Articulation Controller). To show that our proposed CACRL(CA-CMAC-based Reinforcement Learning) performs better than the CRL(CMAC- based Reinforcement Learning), computer simulation and experiment results are illustrated, where a swing-up control Problem of an acrobot is considered.

• 한국BIM학회 논문집
• /
• 제12권2호
• /
• pp.40-48
• /
• 2022

It is very important to accurately predict construction costs in the early stages of the construction project. However, it is difficult to accurately predict construction costs with limited information from the initial stage. In recent years, with the development of machine learning technology, it has become possible to predict construction costs more accurately than before only with schematic construction characteristics. Based on machine learning technology, this study aims to analyze plans to more accurately predict construction costs by using only the factors influencing construction costs. To the end of this study, the effect of the error rate according to the activation function and the node configuration of the hidden layer was analyzed.

• 한국정밀공학회지
• /
• 제13권4호
• /
• pp.75-86
• /
• 1996

In this paper, we propose a new fuzzy-neural network control scheme for the speed and azimuth control of a mobile robot. The proposed control scheme uses a gaussian function as a unit function in the fuzzy-neural network, and back propagation algorithm to train the fuzzy-neural network controller in the frame-work of the specialized learning architecture. It is proposed a learning controller consisting of two fuzzy-neural networks based on independent reasoning and a connection net woth fixed weights to simply the fuzzy-neural network. The effectiveness of the proposed controller is illustrated by performing the computer simulation for a circular trajectory tracking of a mobile robot driven by two independent wheels.

• International Journal of Advanced Culture Technology
• /
• 제5권2호
• /
• pp.74-81
• /
• 2017

Recently, there are many companies that use systems based on artificial intelligence. The accuracy of artificial intelligence depends on the amount of learning data and the appropriate algorithm. However, it is not easy to obtain learning data with a large number of entity. Less data set have large generalization errors due to overfitting. In order to minimize this generalization error, this study proposed DGA(Dropout Genetic Algorithm) which can expect relatively high accuracy even though data with a less data set is applied to machine learning based genetic algorithm to deep learning based dropout. The idea of this paper is to determine the active state of the nodes. Using Gradient about loss function, A new fitness function is defined. Proposed Algorithm DGA is supplementing stochastic inconsistency about Dropout. Also DGA solved problem by the complexity of the fitness function and expression range of the model about Genetic Algorithm As a result of experiments using MNIST data proposed algorithm accuracy is 75.3%. Using only Dropout algorithm accuracy is 41.4%. It is shown that DGA is better than using only dropout.

• 대한원격탐사학회지
• /
• 제36권5_2호
• /
• pp.929-937
• /
• 2020

본 논문에서는 의미론적 분할을 위한 딥러닝 기술 중의 하나인 UNet++ 모델을 이용하여 다시기 위성영상의 변화지역을 탐지하고자 하였다. 다양한 손실함수에 대한 학습결과를 분석하기 위하여, 이진 교차 엔트로피, 자카드 변수에 의하여 학습된 UNet++ 모델에 의한 변화탐지 결과를 평가하였다. 또한, 딥러닝 모델의 결과는 WorldView-3 위성영상을 활용하여 기존의 화소기반 변화탐지 기법의 결과와 비교하여 평가하였다. 실험결과, 손실함수의 특성에 따라서 딥러닝 모델의 성능이 달라질 수 있음을 확인하였으나, 기존 기법들과 비교하여 우수한 결과를 나타내는 것도 확인하였다.

• 한국정보과학회논문지:소프트웨어및응용
• /
• 제30권11호
• /
• pp.1054-1061
• /
• 2003

강화학습의 대표적인 알고리즘인 Q-Learning은 상태공간의 모든 상태-행동 쌍(state-action pairs)의 평가값이 수렴할 때까지 반복해서 경험하여 최적의 전략(policy)을 얻는다. 상태공간을 구성하는 요소(feature)들이 많거나 요소의 데이타 형태가 연속형(continuous)인 경우, 상태공간은 지수적으로 증가하게 되어, 모든 상태들을 반복해서 경험해야 하고 모든 상태-행동 쌍의 Q값을 저장하는 것은 시간과 메모리에 있어서 어려운 문제이다. 본 논문에서는 온라인으로 학습을 진행하면서 비슷한 상황의 상태들을 클러스터링(clustering)하고 새로운 경험에 적응해서 클러스터(cluster)의 수정(update)을 반복하여, 분류된 최적의 전략(policy)을 얻는 새로운 함수근사(function approximation)방법인 Q-Map을 소개한다. 클러스터링으로 인해 정교한 제어가 필요한 상태(state)는 규칙(rule)으로 추출하여 보완하였다. 미로환경과 마운틴 카 문제를 제안한 Q-Map으로 실험한 결과 분류된 지식을 얻을 수 있었으며 가시화된(explicit) 지식의 형태인 규칙(rule)으로도 쉽게 변환할 수 있었다.

• 한국해양공학회지
• /
• 제10권1호
• /
• pp.65-74
• /
• 1996

Up to now, the existing crack growth modelling has used a mathematical approximation but an assumed function have a great influence on this method. Especially, crack growth behavior that shows very strong nonlinearity needed complicated function which has difficulty in setting parameter of it. The main characteristics of neural network modelling to engineering field are simple calculations and absence of assumed function. In this paper, after discussing learning and generalization of neural networks, we performed crack growth modelling on the basis of above learning algorithms. J'-da/dt relation predicted by neural networks shows that test condition with unlearned data is simulated well within estimated mean error(5%).

• 한국멀티미디어학회논문지
• /
• 제24권10호
• /
• pp.1319-1325
• /
• 2021

It is important to remove fog for accurate object recognition and detection during preprocessing because images taken in foggy adverse weather suffer from poor quality of images due to scattering and absorption of light, resulting in poor performance of various vision-based applications. This paper proposes an end-to-end deep learning-based single image de-fogging method using U-Net architecture. The loss function used in the algorithm is a loss function based on Mahalanobis distance with fog features, which solves the problem of domain shifts, and demonstrates superior performance by comparing qualitative and quantitative numerical evaluations with conventional methods. We also design it to generate fog through the VGG19 loss function and use it as the next training dataset.