• 제목/요약/키워드: Backpropagation Neural Network

검색결과 449건 처리시간 0.034초

Recurrent Neural Network with Backpropagation Through Time Learning Algorithm for Arabic Phoneme Recognition

  • Ismail, Saliza;Ahmad, Abdul Manan
    • 제어로봇시스템학회:학술대회논문집
    • /
    • 제어로봇시스템학회 2004년도 ICCAS
    • /
    • pp.1033-1036
    • /
    • 2004
  • The study on speech recognition and understanding has been done for many years. In this paper, we propose a new type of recurrent neural network architecture for speech recognition, in which each output unit is connected to itself and is also fully connected to other output units and all hidden units [1]. Besides that, we also proposed the new architecture and the learning algorithm of recurrent neural network such as Backpropagation Through Time (BPTT, which well-suited. The aim of the study was to observe the difference of Arabic's alphabet like "alif" until "ya". The purpose of this research is to upgrade the people's knowledge and understanding on Arabic's alphabet or word by using Recurrent Neural Network (RNN) and Backpropagation Through Time (BPTT) learning algorithm. 4 speakers (a mixture of male and female) are trained in quiet environment. Neural network is well-known as a technique that has the ability to classified nonlinear problem. Today, lots of researches have been done in applying Neural Network towards the solution of speech recognition [2] such as Arabic. The Arabic language offers a number of challenges for speech recognition [3]. Even through positive results have been obtained from the continuous study, research on minimizing the error rate is still gaining lots attention. This research utilizes Recurrent Neural Network, one of Neural Network technique to observe the difference of alphabet "alif" until "ya".

  • PDF

반도체 패키지의 내부 결함 검사용 알고리즘 성능 향상 (The Performance Advancement of Test Algorithm for Inner Defects in Semiconductor Packages)

  • 김재열;윤성운;한재호;김창현;양동조;송경석
    • 한국정밀공학회:학술대회논문집
    • /
    • 한국정밀공학회 2002년도 추계학술대회 논문집
    • /
    • pp.345-350
    • /
    • 2002
  • In this study, researchers classifying the artificial flaws in semiconductor packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method fur entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

  • PDF

반도체 패키지의 내부 결함 검사용 알고리즘 성능 향상 (The Performance Advancement of Test Algorithm for Inner Defects In Semiconductor Packages)

  • 김재열;김창현;윤성운
    • 한국정밀공학회:학술대회논문집
    • /
    • 한국정밀공학회 2005년도 추계학술대회 논문집
    • /
    • pp.721-726
    • /
    • 2005
  • In this study, researchers classifying the artificial flaws in semiconductor. packages are performed by pattern recognition technology. For this purposes, image pattern recognition package including the user made software was developed and total procedure including ultrasonic image acquisition, equalization filtration, binary process, edge detection and classifier design is treated by Backpropagation Neural Network. Specially, it is compared with various weights of Backpropagation Neural Network and it is compared with threshold level of edge detection in preprocessing method for entrance into Multi-Layer Perceptron(Backpropagation Neural network). Also, the pattern recognition techniques is applied to the classification problem of defects in semiconductor packages as normal, crack, delamination. According to this results, it is possible to acquire the recognition rate of 100% for Backpropagation Neural Network.

  • 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

개선된 유전자 역전파 신경망에 기반한 예측 알고리즘 (Forecasting algorithm using an improved genetic algorithm based on backpropagation neural network model)

  • 윤여창;조나래;이성덕
    • Journal of the Korean Data and Information Science Society
    • /
    • 제28권6호
    • /
    • pp.1327-1336
    • /
    • 2017
  • 본 연구에서는 단기 예측을 위한 자기회귀누적이동평균모형, 역전파 신경망 및 유전자 알고리즘의 결합 적용에 대하여 논의하고 이를 통한 유전자-신경망 알고리즘의 효용성을 살펴본다. 일반적으로 역전파 알고리즘은 지역 최소값에 수렴될 수 있는 단점이 있기 때문에, 여기서는 예측 정확도를 높이기 위해 역전파 신경망 구조를 최적화하고 유전자 알고리즘을 결합한 유전자-신경망 알고리즘 기반 예측모형을 구축한다. 실험을 통한 오차 비교는 KOSPI 지수를 이용한다. 결과는 이 연구에서 제안된 유전자-신경망 모형이 역전파 신경망 모형과 비교할 때 예측 정확도에서 어느 정도 유의한 효율성을 보여주고자 한다.

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

역전파신경망을 이용한 구멍뚫기법의 편심 오차 예측 (Prediction for the Error due to Role Eccentricity in Hole-drilling Method Using Backpropagation Neural Network)

  • 김철;양원호;허성필;정기현
    • 대한기계학회논문집A
    • /
    • 제26권3호
    • /
    • pp.436-444
    • /
    • 2002
  • The measurement of residual stresses by the hole-drilling method has been commonly used to evaluate residual stresses in structural members. In this method, eccentricity can usually occur between the hole center and rosette gage center. In this study, the error due to the hole eccentricity is predicted using the artificial neural network. The neural network has trained training examples of stress ratio, normalized eccentricity, off-centered direction and stress error using backpropagation learning process. The prediction results of the error using the trained neural network are good agreement with FE analyzed ones.

신경회로망을 이용한 평판 맞대기용접의 잔류응력 예측시스템 개발 (Predictive System Evaluation of Residual Stresses of Plate Butt Welding Using Neural Network)

  • 차용훈;성백섭;이연신
    • Journal of Welding and Joining
    • /
    • 제21권1호
    • /
    • pp.80-86
    • /
    • 2003
  • This study develops a system for effective prediction of residual stresses by the backpropagation algorithm using the neural network. To achieve this goal, a series of experiments were carried out to and measured the residual stresses using the sectional method. With the experimental results, the optional control algorithms using a neural network could be developed in order to reduce the effect of the external disturbances during GMA welding processes. Then the results obtained from this study were compared between the measured and calculated results, weld guality might be controlled by the neural network based on backpropagation algorithm.. This system can not only help to understand the interaction between the process parameters and residual stress, but also improve the quantity control for welded structures.

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

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