• 대한수학교육학회지:학교수학
• /
• 제4권3호
• /
• pp.495-511
• /
• 2002

In this paper, we deal with the teaching of parameter in the school mathematics. The roles of letters become different according to the letters-used context. That is, the meaning of letters may change in the course of being used. But specifying the roles of letters without understanding the distinction between the roles is not enough for students to learn the meaning of variables, specifically that of parameters. Therefore, the parameter-learning should focus on the dynamic change of roles. That implies flexible thinking and changing of perspectives.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1988년도 한국자동제어학술회의논문집(국내학술편); 한국전력공사연수원, 서울; 21-22 Oct. 1988
• /
• pp.326-331
• /
• 1988

In this paper, an iterative leaning control algorithm for the linear discrete system is proposed. Based upon the parameter estimation method, the learning for good tracking control is acqured through a sequence of repetitive operations. A series of simulation are performed to show the validity of this algorithm.

• 한국감성과학회:학술대회논문집
• /
• 한국감성과학회 2011년도 추계학술대회
• /
• pp.63-64
• /
• 2011

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 1997년도 춘계학술대회 학술발표 논문집
• /
• pp.180-184
• /
• 1997

This paper presents the fuzzy neural network which utilizes a fuzzified Kohonen learning uses a fuzzy membership value, a function of the iteration, and a intra-membership value instead of a learning rate. The IRIS data set if used to test the fuzzy neural network. The test result shows the performance of the fuzzy neural network depends on k and the vigilance parameter T.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권3호
• /
• pp.911-931
• /
• 2021

Recently, most cloud services use Docker container environment to provide their services. However, there are no researches to evaluate the performance of communication libraries for multi-GPU based distributed deep learning in a Docker container environment. In this paper, we propose an efficient communication architecture for multi-GPU based deep learning in a Docker container environment by evaluating the performances of various communication libraries. We compare the performances of the parameter server architecture and the All-reduce architecture, which are typical distributed deep learning architectures. Further, we analyze the performances of two separate multi-GPU resource allocation policies - allocating a single GPU to each Docker container and allocating multiple GPUs to each Docker container. We also experiment with the scalability of collective communication by increasing the number of GPUs from one to four. Through experiments, we compare OpenMPI and MPICH, which are representative open source MPI libraries, and NCCL, which is NVIDIA's collective communication library for the multi-GPU setting. In the parameter server architecture, we show that using CUDA-aware OpenMPI with multi-GPU per Docker container environment reduces communication latency by up to 75%. Also, we show that using NCCL in All-reduce architecture reduces communication latency by up to 93% compared to other libraries.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 2004년도 학술대회 논문집 정보 및 제어부문
• /
• pp.349-351
• /
• 2004

The classical dynamic backpropagation learning algorithm has the problems of learning speed and the determine of learning parameter. The Extend Kalman Filter(EKF) is used effectively for a state estimation method for a non linear dynamic system. This paper presents a learning algorithm using Dual Extended Kalman Filter(DEKF) for Fully Recurrent Neural Network(FRNN). This DEKF learning algorithm gives the minimum variance estimate of the weights and the hidden outputs. The proposed DEKF learning algorithm is applied to the system identification of a nonlinear SISO system and compared with dynamic backpropagation learning algorithm.

• 말소리와 음성과학
• /
• 제3권3호
• /
• pp.91-98
• /
• 2011

In this paper, a multi-channel speech enhancement method using the linearly constrained minimum variance (LCMV) algorithm and a variable learning rate control is proposed. To control the learning rate for adaptive filters of the LCMV algorithm, the direction of arrival (DOA) is measured for each short-time input signal and the likelihood function of the target speech presence is estimated to control the filter learning rate. Using the likelihood measure, the learning rate is increased during the pure noise interval and decreased during the target speech interval. To optimize the parameter of the mapping function between the likelihood value and the corresponding learning rate, an exhaustive search is performed using the Bark's scale distortion (BSD) as the performance index. Experimental results show that the proposed algorithm outperforms the conventional LCMV with fixed learning rate in the BSD by around 1.5 dB.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.333-336
• /
• 1997

In this paper, we present a nonlinear dynamic controller for position tracking of brushless dc motors. In constructing the controller, a backstepping-type approach is used under the condition of full state information, while an adaptive controller is adopted for parameter uncertainty throughout the entire electromechanical system. The nonlinear dynamic controller using the adaptive learning technique approach is shown to drive the state variables of system to the desired ones asymptotically and whose effectiveness is also sown via computer simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1997년도 한국자동제어학술회의논문집; 한국전력공사 서울연수원; 17-18 Oct. 1997
• /
• pp.636-639
• /
• 1997

In this paper, a dynamic control scheme is proposed which not only compensates for the lateral dynamics and longitudinal dynamics but also deal with the yaw motion dynamics. Using the dynamic control technique, adaptive and learning algorithm together, the proposed controller is not only robust to disturbance and parameter uncertainties but also can learn the inverse dynamics model in steady state. Based on the proposed dynamic control scheme, a dynamic vehicle simulator is contructed to design and test various control techniques for 4-wheel steering vehicles.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.810-813
• /
• 2002

We present the information theoretic learning based on the Tsallis entropy maximization principle for various q. The Tsallis entropy is one of the generalized entropies and is a canonical entropy in the sense of physics. Further, we consider the dependency of the learning on the parameter $\sigma$, which is a standard deviation of an assumed a priori distribution of samples such as Parzen window.