• 제목/요약/키워드: Back Propagation Training Algorithm

검색결과 185건 처리시간 0.028초

Self-Relaxation for Multilayer Perceptron

  • Liou, Cheng-Yuan;Chen, Hwann-Txong
    • 한국지능시스템학회:학술대회논문집
    • /
    • 한국퍼지및지능시스템학회 1998년도 The Third Asian Fuzzy Systems Symposium
    • /
    • pp.113-117
    • /
    • 1998
  • We propose a way to show the inherent learning complexity for the multilayer perceptron. We display the solution space and the error surfaces on the input space of a single neuron with two inputs. The evolution of its weights will follow one of the two error surfaces. We observe that when we use the back-propagation(BP) learning algorithm (1), the wight cam not jump to the lower error surface due to the implicit continuity constraint on the changes of weight. The self-relaxation approach is to explicity find out the best combination of all neurons' two error surfaces. The time complexity of training a multilayer perceptron by self-relaxationis exponential to the number of neurons.

  • PDF

역전파 학습의 오차함수 개선에 의한 다층퍼셉트론의 학습성능 향상 (Improving the Error Back-Propagation Algorithm of Multi-Layer Perceptrons with a Modified Error Function)

  • 오상훈;이영직
    • 전자공학회논문지B
    • /
    • 제32B권6호
    • /
    • pp.922-931
    • /
    • 1995
  • In this paper, we propose a modified error function to improve the EBP(Error Back-Propagation) algorithm of Multi-Layer Perceptrons. Using the modified error function, the output node of MLP generates a strong error signal in the case that the output node is far from the desired value, and generates a weak error signal in the opposite case. This accelerates the learning speed of EBP algorothm in the initial stage and prevents overspecialization for training patterns in the final stage. The effectiveness of our modification is verified through the simulation of handwritten digit recognition.

  • PDF

신경망을 이용한 열간단조품의 초기 소재 설계 (Design of Initial Billet using the Artificial Neural Network for a Hot Forged Product)

  • Kim, D.J.;Kim, B.M.;Park, J.C.
    • 한국정밀공학회지
    • /
    • 제12권11호
    • /
    • pp.118-124
    • /
    • 1995
  • In the paper, we have proposed a new technique to determine the initial billet for the forged products using a function approximation in neural network. A three-layer neural network is used and a back propagation algorithm is employed to train the network. An optimal billet which satisfied the forming limitation, minimum of incomplete filling in the die cavity, load and energy as well as more uniform distribution of effective strain, is determined by applying the ability of function approximation of the neural network. The amount of incomplete filling in the die, load and forming energy as well as effective strain are measured by the rigid-plastic finite element method. This new technique is applied to find the optimal billet size for the axisymmetric rib-web product in hot forging. This would reduce the number of finite element simulation for determining the optimal billet of forging products, further it is usefully adopted to physical modeling for the forging design

  • PDF

PID 학습제어기를 이용한 가변부하 직류서보전동기의 실시간 제어 (Real-Time Control of DC Sevo Motor with Variable Load Using PID-Learning Controller)

  • 김상훈;정인석;강영호;남문현;김낙교
    • 대한전기학회논문지:시스템및제어부문D
    • /
    • 제50권3호
    • /
    • pp.107-113
    • /
    • 2001
  • This paper deals with speed control of DC servo motor using a PID controller with a gain tuning based on a Back-Propagation(BP) Learning Algorithm. Conventionally a PID controller has been used in the industrial control. But a PID controller should produce suitable parameters for each system. Also, variables of the PID controller should be changed according to environments, disturbances and loads. In this paper described by a experiment that contained a method using a PID controller with a gain tuning based on a Back-Propagation(BP) Learning Algorithm, we developed speed characteristics of a DC servo motor on variable loads. The parameters of the controller are determined by neural network performed on on-line system after training the neural network on off-line system.

  • PDF

신경회로망에 의한 음성 및 잡음 인식 시스템 (Speech and Noise Recognition System by Neural Network)

  • 최재승
    • 한국전자통신학회논문지
    • /
    • 제5권4호
    • /
    • pp.357-362
    • /
    • 2010
  • 본 논문에서는 음성 및 잡음 구간을 검출하기 위하여 신경회로망에 의한 음성 및 잡음 인식시스템을 제안한다. 제안하는 신경회로망은 오차역전파알고리즘에 의하여 학습되는 네트워크이다. 먼저, 고속 푸리에변환에 의한 전력스펙트럼 및 선형예측계수가 각 프레임에서 신경회로망의 입력으로 사용되어 네트워크가 학습된다. 따라서 제안된 신경회로망은 잡음이 중첩되지 않은 음성 및 잡음을 사용하여 학습된다. 제안한 인식시스템의 성능은 다양한 음성 및 백색, 프린터, 도로, 자동차 잡음 들을 사용하여 인식율에 의하여 평가된다. 본 실험에서는 신경회로망의 학습 데이터 및 평가 데이터가 다를 경우에도 이러한 음성 및 잡음에 대하여 92% 이상의 인식율을 구할 수 있었다.

신경회로망과 실험계획법을 이용한 칩형상 예측 (Prediction of Chip Forms using Neural Network and Experimental Design Method)

  • 한성종;최진필;이상조
    • 한국정밀공학회지
    • /
    • 제20권11호
    • /
    • pp.64-70
    • /
    • 2003
  • This paper suggests a systematic methodology to predict chip forms using the experimental design technique and the neural network. Significant factors determined with ANOVA analysis are used as input variables of the neural network back-propagation algorithm. It has been shown that cutting conditions and cutting tool shapes have distinct effects on the chip forms, so chip breaking. Cutting tools are represented using the Z-map method, which differs from existing methods using some chip breaker parameters. After training the neural network with selected input variables, chip forms are predicted and compared with original chip forms obtained from experiments under same input conditions, showing that chip forms are same at all conditions. To verify the suggested model, one tool not used in training the model is chosen and input to the model. Under various cutting conditions, predicted chip forms agree well with those obtained from cutting experiments. The suggested method could reduce the cost and time significantly in designing cutting tools as well as replacing the“trial-and-error”design method.

신경회로망을 이용한 자동조종장치 설계 (An application of neural network to autopilot design)

  • 유재종;송찬호
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 1993년도 한국자동제어학술회의논문집(국내학술편); Seoul National University, Seoul; 20-22 Oct. 1993
    • /
    • pp.619-623
    • /
    • 1993
  • In this paper, a neural network is appled to design a lateral autopilot for airplanes. Linearized lateral dynamics is used in training the neural network controller and verifying the performance as well. To train the neural network, back propagation algorithm is used. In this training, no information about the dynamics to be controlled except sign and rough magnitude of control derivatives is needed. It is shown by computer simulations that the performance and stability margin are satisfactory.

  • PDF

함수근사를 위한 로버스트 역전파 알고리즘 (A Robust Propagation Algorithm for Function Approximation)

  • 김상민;황창하
    • 한국정보처리학회논문지
    • /
    • 제4권3호
    • /
    • pp.747-753
    • /
    • 1997
  • 함수근사는 과학과 공학분야에서 광범위하게 응용된다. 다층 전방향 신경망은 비선형 함수근사를 위한 도구로서 제안되어져 왔으며, 다층 신경망을 학습시키기 위한 학습 알고리즘으로 역전파 알고리즘이 널리 이용되어져 왔다. 그러나 이상치(outlier) 를 포함한 학습자료가 존재할 때에는 학습되는 함수는 존재하는 모든 자료 사이를 보간 하므로 이상치가 있는 자료의 위치까지도 보간 하여, 원하지 않은 구조를 파악하게 된다. 따라서 이상치의 영향을 최소화 시키기 위해 본 논문에서는 로버스트 에너지 함수를 유도하여 개량된 로버스트 역전파 알고리즘을 제안한다.

  • PDF

퍼지 신경회로망을 이용한 원격감지 영상의 분류 (Classification of remotely sensed images using fuzzy neural network)

  • 이준재;황석윤;김효성;이재욱;서용수
    • 전자공학회논문지S
    • /
    • 제35S권3호
    • /
    • pp.150-158
    • /
    • 1998
  • This paper describes the classification of remotely sensed image data using fuzzy neural network, whose algorithm was obtained by replacing real numbers used for inputs and outputs in the standard back propagation algorithm with fuzzy numbers. In the proposed method, fuzzy patterns, generated based on the histogram ofeach category for the training data, are put into the fuzzy neural network with real numbers. The results show that the generalization and appoximation are better than that ofthe conventional network in determining the complex boundary of patterns.

  • PDF

신경회로망을 이용한 비선형 시스팀 제어의 실험적 연구 (Experimental Studies of Neural Network Control Technique for Nonlinear Systern)

  • 임선빈;정슬
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2000년도 제15차 학술회의논문집
    • /
    • pp.195-195
    • /
    • 2000
  • In this paper, intelligent control method using neural network as a nonlinear controller is presented, Neural network controller is implemented on DSP board in PC to make real time computing possible, On-line training algorithm for neural network control is proposed, As a test-bed, a large a-x table was build and interface with PC has been implemented, Experimental results under different PD controller gains show excellent position tracking for circular trajectory compared with those for PD controller only.

  • PDF