• 제목/요약/키워드: Backpropagation Neural Networks

검색결과 230건 처리시간 0.03초

Improve Digit Recognition Capability of Backpropagation Neural Networks by Enhancing Image Preprocessing Technique

  • Feng, Xiongfeng;Kubik, K.Bogunia
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2001년도 ICCAS
    • /
    • pp.49.4-49
    • /
    • 2001
  • Digit recognition based on backpropagation neural networks, as an important application of pattern recognition, was attracted much attention. Although it has the advantages of parallel calculation, high error-tolerance, and learning capability, better recognition effects can only be achieved with some specific fixed format input of the digit image. Therefore, digit image preprocessing ability directly affects the accuracy of recognition. Here using Matlab software, the digit image was enhanced by resizing and neutral-rotating the extracted digit image, which improved the digit recognition capability of the backpropagation neural network under practical conditions. This method may also be helpful for recognition of other patterns with backpropagation neural networks.

  • PDF

Using Classification function to integrate Discriminant Analysis, Logistic Regression and Backpropagation Neural Networks for Interest Rates Forecasting

  • Oh, Kyong-Joo;Ingoo Han
    • 한국지능정보시스템학회:학술대회논문집
    • /
    • 한국지능정보시스템학회 2000년도 추계정기학술대회:지능형기술과 CRM
    • /
    • pp.417-426
    • /
    • 2000
  • This study suggests integrated neural network models for Interest rate forecasting using change-point detection, classifiers, and classification functions based on structural change. The proposed model is composed of three phases with tee-staged learning. The first phase is to detect successive and appropriate structural changes in interest rare dataset. The second phase is to forecast change-point group with classifiers (discriminant analysis, logistic regression, and backpropagation neural networks) and their. combined classification functions. The fecal phase is to forecast the interest rate with backpropagation neural networks. We propose some classification functions to overcome the problems of two-staged learning that cannot measure the performance of the first learning. Subsequently, we compare the structured models with a neural network model alone and, in addition, determine which of classifiers and classification functions can perform better. This article then examines the predictability of the proposed classification functions for interest rate forecasting using structural change.

  • PDF

신경망 이론을 이용한 통행발생 모형연구 (선형/비선형 회귀모형과의 비교) (Trip Generation Model Using Backpropagation Neural Networks in Comparison with linear/nonlinear Regression Analysis)

  • 장수은;김대현;임강원
    • 대한교통학회지
    • /
    • 제18권4호
    • /
    • pp.95-105
    • /
    • 2000
  • 본 연구의 목적은 기존의 대표적 통행발생모형인 회귀모형과 신경망 이론에 의한 통행발생모형을 비교.분석하여 통행발생모형에 대한 새로운 방법을 제시하고자 하는 것이다. 이를 위해 모형의 검정력과 안정성을 현재적 설명력과 장래 예측력의 결합으로 전제하고, 시나리오에 따른 모형의 검정력 변화를 통한 안정성 평가를 수행하였다. 연구결과 역전파 신경망 모형(Backpropagation Neural Networks)은 회귀모형의 검정력과 안정성을 상회하는 우수한 결과를 보여 주었으며, 이는 향후 통행발생 모형으로 역전파 신경망 모형의 적용 가능성을 의미하는 것으로 해석된다. 특히 복잡해진 교통현상과 다양한 수집자료를 고려할 때 교통분야에서의 신경망 모형의 적용은 더욱 확대될 전망이다.

  • PDF

다중 역전파 신경망을 이용한 차량 번호판의 인식 (Recognition of vehicle number plate using multi backpropagation neural network)

  • 최재호;조범준
    • 한국통신학회논문지
    • /
    • 제22권11호
    • /
    • pp.2432-2438
    • /
    • 1997
  • 본 논문은 CCD 카메라로부터 얻어진 차량 영상에서 번호판 영역이 일정한 패턴의 광강도를 지니는 특징을 이용하여 번호판 영역을 추출학 문자인식을 개선하기 위하여 단일 역전파 신경망 대신 다중 역전파 신경망으로 차량 번호판 인식 시스템을 구현하였다. 본 논문의 실험 결과, 효율적인 문자 영역의 추출이 가능하고, 기존의 단일 역전파 방법보다 학습 시간이 단축되고 인식율이 향상됨을 보인다.

  • PDF

새로운 다층 신경망 학습 알고리즘 (A new learning algorithm for multilayer neural networks)

  • 고진욱;이철희
    • 대한전자공학회:학술대회논문집
    • /
    • 대한전자공학회 1998년도 추계종합학술대회 논문집
    • /
    • pp.1285-1288
    • /
    • 1998
  • In this paper, we propose a new learning algorithm for multilayer neural networks. In the error backpropagation that is widely used for training multilayer neural networks, weights are adjusted to reduce the error function that is sum of squared error for all the neurons in the output layer of the network. In the proposed learning algorithm, we consider each output of the output layer as a function of weights and adjust the weights directly so that the output neurons produce the desired outputs. Experiments show that the proposed algorithm outperforms the backpropagation learning algorithm.

  • PDF

신경회로망을 이용한 복합재료 원통쉘의 하중특성 추론에 관한 연구 (A Study on the Prediction of the Loaded Location of the Composite Laminated Shell by Using Neural Networks)

  • 명창문;이영신;류충현
    • Composites Research
    • /
    • 제14권5호
    • /
    • pp.26-37
    • /
    • 2001
  • 본 연구에서는 복합재료 원통쉘의 구조해석을 통하여 구해진 원통쉘 경사면의 10등분 등간격 9지점의 변형율을 신경회로망의 입력패턴으로 활용하여 원통쉘에 가해진 중격하중 특성을 동시에 추론하였다. 적용된 신경회로망은 Momentum Backpropagation 알고리즘이며, 모멘텀 계수 및 학습율이 학습도에 따라 가변적으로 조정될 수 있도록 프로그램을 개발 적용하였다 Backpropagation 신경회로망의 은닉층은 1층에서 3층까지 별도 프로그램을 개발하여 충격하중 특성추론 학습을 시도하였다. 개발된 신경회로망 프로그램을 적용하여 원통쉘의 충격하중 특성추론 정확도는 1%이내로 학습에 성공하였다. 본 연구 결과 신경회로망을 이용한 복합재료 원통쉘의 충격하중 특성을 추론할 수 있는 역문제 해석이 가능해졌다.

  • PDF

Using Structural Changes to support the Neural Networks based on Data Mining Classifiers: Application to the U.S. Treasury bill rates

  • 오경주
    • 한국데이터정보과학회:학술대회논문집
    • /
    • 한국데이터정보과학회 2003년도 추계학술대회
    • /
    • pp.57-72
    • /
    • 2003
  • This article provides integrated neural network models for the interest rate forecasting using change-point detection. The model is composed of three phases. The first phase is to detect successive structural changes in interest rate dataset. The second phase is to forecast change-point group with data mining classifiers. The final phase is to forecast the interest rate with BPN. Based on this structure, we propose three integrated neural network models in terms of data mining classifier: (1) multivariate discriminant analysis (MDA)-supported neural network model, (2) case based reasoning (CBR)-supported neural network model and (3) backpropagation neural networks (BPN)-supported neural network model. Subsequently, we compare these models with a neural network model alone and, in addition, determine which of three classifiers (MDA, CBR and BPN) can perform better. For interest rate forecasting, this study then examines the predictability of integrated neural network models to represent the structural change.

  • PDF

신경회로망을 이용한 원통셀의 충격하중 추론에 관한 연구 (Identification of Composite Cylindricall shells by Using Neural Networks)

  • 명창문;이영신
    • 한국소음진동공학회논문집
    • /
    • 제11권9호
    • /
    • pp.475-485
    • /
    • 2001
  • A study on the structural analysis of the composite laminated cylindrical shell which has simply supported boundary conditions at both ends, was performed. The results were used into the neural networks. Neural networks identify the load characteristics of the composite shells. Momentum Backpropagation which the learning rate can be varied was developed. Input patterns consist of strains at 9 side points which is divided equally. Output layers are the load characteristics. Developed program was used for the training. The training with variable learning rate was converged close to real oad characteristics. Inverse engineering can be applicable to the composite laminated cylindrical shells with developed neural networks.

  • PDF

카오틱 신경망을 이용한 적응제어에 관한 연구 (A study on the Adaptive Neural Controller with Chaotic Neural Networks)

  • Sang Hee Kim;Won Woo Park;Hee Wook Ahn
    • 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.

  • PDF

Improved Learning Algorithm with Variable Activating Functions

  • Pak, Ro-Jin
    • Journal of the Korean Data and Information Science Society
    • /
    • 제16권4호
    • /
    • pp.815-821
    • /
    • 2005
  • Among the various artificial neural networks the backpropagation network (BPN) has become a standard one. One of the components in a neural network is an activating function or a transfer function of which a representative function is a sigmoid. We have discovered that by updating the slope parameter of a sigmoid function simultaneous with the weights could improve performance of a BPN.

  • PDF