• 인지과학
• /
• 제4권2호
• /
• pp.181-200
• /
• 1994

다층 신경망의 학습에 있어서 역전파 알고리즘은 시스템이 지역적 최소치에 빠질수 있고,탐색공간의 피라미터들에 의해 신경망 시스템의 성능이 크게 좌우된다는 단점이 있다.이러한 단점을 보완하기 의해 유전자 알고리즘이 신경망의 학습에 도입도었다.그러나 유전자 알고리즘에는 역전파 알고리즘과 같은 미세 조정되는 지역적 탐색(fine-tuned local search) 을 위한 메카니즘이 존재하지 않으므로 시스템이 전역적 최적해로 수렴하는데 많은 시간을 필요로 한다는 단점이 있다. 따라서 본 논문에서는 역전파 알고리즘의 기울기 강하 기법(gradient descent method)을 교배나 돌연변이와 같은 유전 연산자로 둠으로써 유전자 알고리즘에 지역적 미세 조정(local fine-tuning)을 위한 메카니즘을 제공해주는 새로운 형태의 GA-BP 방법을 제안한다.제안된 방법의 유용성을 보이기 위해 3-패러티 비트(3-parity bit) 문제에 실험하였다.

• 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.

• 한국지능시스템학회논문지
• /
• 제5권2호
• /
• pp.70-78
• /
• 1995

입출력 데이터를 이용한 퍼지모델의 설정은 구조 설정과 변수 설정으로 나누어진다. 본 논문에서는 기존 방법의 문제점을 해결하고 퍼지모델의 이러한 구조와 변수를 설정하는 새로운 방법을 제안한다. 입출력 데이터가 주어지면, 후건부 변수는 선형성과연속성을 고려하여 휴(Hough) 변환과클러스터링 방법에 의해 각각 설정된다. 또한 경사 하강법(Gradient descent method)을 사용하여 퍼지모델 변수의 미세조정을 행한다. 마지막으로 단일 입출력 시스템에 대하여 시뮬레이션을 통해 제안된 방법의 유효성을 보인다.

• 한국지능시스템학회:학술대회논문집
• /
• 한국퍼지및지능시스템학회 2002년도 추계학술대회 및 정기총회
• /
• pp.113-117
• /
• 2002

PID controllers, which have been widely used in industry, have a simple structure and robustness to modeling error. But it is difficult to have uniformly good control performance in system parameters variation or different velocity command. In this paper, we propose a nonlinear adaptive PR controller based on an Immune feedback mechanism and a gradient descent teaming. This algorithm has a simple structure and robustness to system parameters variation. To verify performances of the proposed nonlinear adaptive PID controller, the speed control of nonlinear DC motor Is peformed. The simulation results show that the proposed control systems are effective in tracking a command velocity under system parameters variation

• 한국지능시스템학회논문지
• /
• 제14권1호
• /
• pp.118-124
• /
• 2004

In this paper, we present a indirect adaptive control method using a wavelet neural network (WNN) for the control of chaotic nonlinear systems without precise mathematical models. The proposed indirect adaptive control method includes the off-line identification and on-line control procedure for chaotic nonlinear systems. In the off-line identification procedure, the WNN based identification model identifies the chaotic nonlinear system by using the serial-parallel identification structure and is trained by the gradient-descent method. And, in the on-line control procedure, a WNN controller is designed by using the off-line identification model and is trained by the error back-propagation algorithm. Finally, the effectiveness and feasibility of the proposed control method is demonstrated with applications to the chaotic nonlinear systems.

• Journal of Mechanical Science and Technology
• /
• 제15권5호
• /
• pp.580-591
• /
• 2001

This paper proposes a fuzzy-sliding mode control which is designed by a self tuning fuzzy inference method based on a genetic algorithm. Using the method, the number of inference rules and the shape of the membership functions of the proposed fuzzy-sliding mode control are optimized without the aid of an expert in robotics. The fuzzy outputs of the consequent part are updated by the gradient descent method. It is further guaranteed that the selected solution becomes the global optimal solution by optimizing Akaikes information criterion expressing the quality of the inference rules. In order to evaluate the learning performance of the proposed fuzzy-sliding mode control based on a genetic algorithm, a trajectory tracking simulation of the polishing robot is carried out. Simulation results show that the optimal fuzzy inference rules are automatically selected by the genetic algorithm and the trajectory control result is similar to the result of the fuzzy-sliding mode control which is selected through trial error by an expert. Therefore, a designer who does not have expert knowledge of robot systems can design the fuzzy-sliding mode controller using the proposed self tuning fuzzy inference method based on the genetic algorithm.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제2권2호
• /
• pp.159-165
• /
• 2002

This paper proposes a GA and Gradient Descent Method-based method for choosing an appropriate set of fuzzy rules for classification problems. The aim of the proposed method is to fond a minimum set of fuzzy rules that can correctly classify all training patterns. The number of inference rules and the shapes of the membership functions in the antecedent part of the fuzzy rules are determined by the genetic algorithms. The real numbers in the consequent parts of the fuzzy rules are obtained through the use of the descent method. A fitness function is used to maximize the number of correctly classified patterns, and to minimize the number of fuzzy rules. A solution obtained by the genetic algorithm is a set of fuzzy rules, and its fitness is determined by the two objectives, in a combinatorial optimization problem. In order to demonstrate the effectiveness of the proposed method, computer simulation results are shown.

• 한국정보통신학회논문지
• /
• 제10권2호
• /
• pp.276-282
• /
• 2006

본 연구에서는 구조가 단순한 PID 제어기의 장점을 살리고, 시스템 파라메터의 변동에 대하여 강인성 성능을 내는 온라인 적응 PID 제어 시스템을 개발하고자 한다. 또한, 제안된 적응 제어 시스템의 초기 제어 구간에서 안정한 스타트-엎(start-up)을 보장하기 위하여 초기 제어기의 이득을 적절한 이득으로 설정하고, 그 이득의 변화량을 경사 감소법에 의하여 학습하는 방법으로 수정 제안하고자 한다. 제안된 적응 PID제어기의 성능 평가를 위하여 비선형 DC 모터의 가변 속도제어에 적용하고, 결과를 모의실험을 통하여 보이고자한다.

• 한국수자원학회:학술대회논문집
• /
• 한국수자원학회 2017년도 학술발표회
• /
• pp.392-395
• /
• 2017

본 연구에서는 일 증발접시 증발량 산정을 위한 딥러닝 (deep learning) 모형의 적용성을 평가하였다. 본 연구에서 적용된 딥러닝 모형은 deep belief network (DBN) 기반 deep neural network (DNN) (DBN-DNN) 모형이다. 모형 적용성 평가를 위하여 부산 관측소에서 측정된 기상자료를 활용하였으며, 증발량과의 상관성이 높은 기상변수들 (일사량, 일조시간, 평균지상온도, 최대기온)의 조합을 고려하여 입력변수집합 (Set 1, Set 2, Set 3)별 모형을 구축하였다. DBN-DNN 모형의 성능은 통계학적 모형성능 평가지표 (coefficient of efficiency, CE; coefficient of determination, $r^2$; root mean square error, RMSE; mean absolute error, MAE)를 이용하여 평가되었으며, 기존의 두가지 형태의 ANN (artificial neural network), 즉 모형학습 시 SGD (stochastic gradient descent) 및 GD (gradient descent)를 각각 적용한 ANN-SGD 및 ANN-GD 모형과 비교하였다. 효과적인 모형학습을 위하여 각 모형의 초매개변수들은 GA (genetic algorithm)를 이용하여 최적화하였다. 그 결과, Set 1에 대하여 ANN-GD1 모형, Set 2에 대하여 DBN-DNN2 모형, Set 3에 대하여 DBN-DNN3 모형이 가장 우수한 모형 성능을 나타내는 것으로 분석되었다. 비록 비교 모형들 사이의 모형성능이 큰 차이를 보이지는 않았으나, 모든 입력집합에 대하여 DBN-DNN3, DBN-DNN2, ANN-SGD3 순으로 모형 효율성이 우수한 것으로 나타났다.

• ETRI Journal
• /
• 제35권2호
• /
• pp.193-199
• /
• 2013

This paper addresses nonnegative independent component analysis (NICA), with the aim to realize the blind separation of nonnegative well-grounded independent source signals, which arises in many practical applications but is hardly ever explored. Recently, Bertrand and Moonen presented a multiplicative NICA (M-NICA) algorithm using multiplicative update and subspace projection. Based on the principle of the mutual correlation minimization, we propose another novel cost function to evaluate the diagonalization level of the correlation matrix, and apply the multiplicative exponentiated gradient (EG) descent update to it to maintain nonnegativity. An efficient approach referred to as the EG-NICA algorithm is derived and its validity is confirmed by numerous simulations conducted on different types of source signals. Results show that the separation performance of the proposed EG-NICA algorithm is superior to that of the previous M-NICA algorithm, with a better unmixing accuracy. In addition, its convergence speed is adjustable by an appropriate user-defined learning rate.