• 전자공학회논문지B
• /
• 제33B권4호
• /
• pp.201-208
• /
• 1996

This paper proposes an efficient method for improving the training performance of the neural network using a hybrid of backpropagation algorithm and dynamic tunneling system.The backpropagation algorithm, which is the fast gradient descent method, is applied for high-speed optimization. The dynamic tunneling system, which is the deterministic method iwth a tunneling phenomenone, is applied for blobal optimization. Converging to the local minima by using the backpropagation algorithm, the approximate initial point for escaping the local minima is estimated by the pattern classification, and the simulation results show that the performance of proposed method is superior th that of backpropagation algorithm with randomized initial point settings.

• 한국정보처리학회논문지
• /
• 제4권11호
• /
• pp.2769-2779
• /
• 1997

본 논문에서는 공액기울기법과 터널링 시스템을 조합사용하여 신경망의 학습성능을 향상시킬 수 있는 효율적인 방법을 제안하였다. 빠른 수렴속도의 학습을 위하여 공액 기울기법에 기초한 후향전파 알고리즘을 사용하였고, 국소최적해를 만났을 때 이를 벗어난 다른 연결가중치의 설정을 위해 동적터널링 시스템에 기초한 후향전파 알고리즘을 조합한 학습 알고리즘을 적용하였다. 제안된 방법을 패리티 검사 및 패턴분류 문제에 각각 적용하여 기존의 기울기 하강법에 기초한 후향전파 알고리즘 및 기울기 하강법과 동적터널링 시스템을 조합한 후향전파 알고리즘방법의 결과와 비교 고찰하여 제안된 방법이 다른 방법들 보다 학습성능에서 우수함을 나타내었다．

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제7권4호
• /
• pp.236-241
• /
• 2007

This paper presents an adaptive controller using chaotic dynamic neural networks(CDNN) for nonlinear dynamic system. A new dynamic backpropagation learning method of the proposed chaotic dynamic neural networks is developed for efficient learning, and this learning method includes the convergence for improving the stability of chaotic neural networks. The proposed CDNN is applied to the system identification of chaotic system and the adaptive controller. The simulation results show good performances in the identification of Lorenz equation and the adaptive control of nonlinear system, since the CDNN has the fast learning characteristics and the robust adaptability to nonlinear dynamic system.

• 융합신호처리학회논문지
• /
• 제4권3호
• /
• pp.41-48
• /
• 2003

본 논문은 개선된 카오틱 신경망을 이용한 비선형 시스템의 적응제어에 관한 것이다. 개선된 카오틱 신경망은 기존의 카오틱 신경망을 간략화하며 동적 특성을 강화하기 위하여 제안하였다 또한 새로운 동적 역전파 학습방법을 개발하였다. 제안된 신경회로망은 다변수 시스템의 시스템식별과 신경망 적응제어 시스템에 적용하였다. 제안된 신경망은 비선형 동적시스템에 우수한 적응성을 가지므로 시뮬레이션 결과는 우수한 성능을 보였다.

• 전자공학회논문지B
• /
• 제31B권10호
• /
• pp.149-157
• /
• 1994

A method of applying a recurrent backpropagation network to identifying or modelling a dynamic system is proposed. After the recurrent backpropagation network having both the characteristicsof interpolative network and associative network is applied to XOR problem, a new model of recurrent backpropagation network is proposed and compared with the original recurrent backpropagation network by applying them to XOR problem. based on the observation thata function can be approximated with polynomials to arbitrary accuracy, the new model is developed so that it may generate higher-order terms in the internal states Moreover, it is shown that the new network is succesfully applied to recognizing noisy patterns of numbers.

• 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.

• 산업기술연구
• /
• 제16권
• /
• pp.197-205
• /
• 1996

In this paper, we propose a new neural architecture. We synthesize the architecture from a combination of structures known as MRCCN (Multi-resolution Radial-basis Competitive and Cooperative Network) and BPN (Backpropagation Network). The proposed neural network is able to improve the learning speed of MRCCN and the mapping capability of BPN. The ability and effectiveness of identifying a ninlinear dynamic system using the proposed architecture will be demonstrated by computer simulation.

• Journal of information and communication convergence engineering
• /
• 제13권2호
• /
• pp.123-131
• /
• 2015

Training neural networks is a complex task with great importance in the field of supervised learning. In the training process, a set of input-output patterns is repeated to an artificial neural network (ANN). From those patterns weights of all the interconnections between neurons are adjusted until the specified input yields the desired output. In this paper, a new hybrid algorithm is proposed for global optimization of connection weights in an ANN. Dynamic swarms are shown to converge rapidly during the initial stages of a global search, but around the global optimum, the search process becomes very slow. In contrast, the gradient descent method can achieve faster convergence speed around the global optimum, and at the same time, the convergence accuracy can be relatively high. Therefore, the proposed hybrid algorithm combines the dynamic particle swarm optimization (DPSO) algorithm with the backpropagation (BP) algorithm, also referred to as the DPSO-BP algorithm, to train the weights of an ANN. In this paper, we intend to show the superiority (time performance and quality of solution) of the proposed hybrid algorithm (DPSO-BP) over other more standard algorithms in neural network training. The algorithms are compared using two different datasets, and the results are simulated.

• 제어로봇시스템학회:학술대회논문집
• /
• 제어로봇시스템학회 1989년도 한국자동제어학술회의논문집; Seoul, Korea; 27-28 Oct. 1989
• /
• pp.1113-1119
• /
• 1989

Neural network control has many innovative potentials for intelligent adaptive control. Among many, it promises real time adaption, robustness, fault tolerance, and self-learning which can be achieved with little or no system models. In this paper, a dynamic robot controller has been developed based on a backpropagation neural network. It gradually learns the robot's dynamic properties through repetitive movements being initially trained with a PD controller. Its control performance has been tested on a simulated PUMA 560 demonstrating fast learning and convergence.

• 한국산학기술학회:학술대회논문집
• /
• 한국산학기술학회 2007년도 춘계학술발표논문집
• /
• pp.147-149
• /
• 2007

"Dynamic Neural Unit"(DNU) based upon the topology of a reverberating circuit in a neuronal pool of the central nervous system. In this thesis, we present a genetic DNU-control scheme for unknown nonlinear systems. Our methodis different from those using supervised learning algorithms, such as the backpropagation (BP) algorithm, that needs training information in each step. The contributions of this thesis are the new approach to constructing neural network architecture and its trainin.