• Title/Summary/Keyword: 온라인 파라메터 학습

Search Result 6, Processing Time 0.019 seconds

Online Learning for Bayesian Network Parameters from Incomplete Data (불완전한 데이터로부터 베이지안 네트워크 파라메터의 온라인 학습)

  • Lim Sungsoo;Cho Sung-Bae
    • Proceedings of the Korean Information Science Society Conference
    • /
    • 2005.11b
    • /
    • pp.652-654
    • /
    • 2005
  • 베이지안 네트워크의 파라메터 학습은 주어진 평가 척도에 따라 데이터의 훈련집합에 가장 잘 부합되는 네트워크 파라메터를 구하는 것으로, 베이지안 네트워크 설계에 드는 시간과 노력을 줄이기 위해 연구되어 왔다. 본 논문에서는 불완전한 데이터로부터 온라인으로 베이지안 네트워크의 파라메터를 학습하는 방법을 제안한다. 제안하는 방법은 불완전한 데이터로부터 학습이 가능하도록 하여 학습의 유연성을 높이고, 온라인 학습을 통해 사용자 또는 환경의 변화를 잘 모델링한다. Choen 등이 제안한 온라인 파라메터 학습 방법인 Voting EM 알고리즘과 비교 실험 결과, 제안하는 방법의 유용성을 확인할 수 있었다.

  • PDF

Online Learning of Bayesian Network Parameters for Incomplete Data of Real World (현실 세계의 불완전한 데이타를 위한 베이지안 네트워크 파라메터의 온라인 학습)

  • Lim, Sung-Soo;Cho, Sung-Bae
    • Journal of KIISE:Computer Systems and Theory
    • /
    • v.33 no.12
    • /
    • pp.885-893
    • /
    • 2006
  • The Bayesian network(BN) has emerged in recent years as a powerful technique for handling uncertainty iii complex domains. Parameter learning of BN to find the most proper network from given data set has been investigated to decrease the time and effort for designing BN. Off-line learning needs much time and effort to gather the enough data and since there are uncertainties in real world, it is hard to get the complete data. In this paper, we propose an online learning method of Bayesian network parameters from incomplete data. It provides higher flexibility through learning from incomplete data and higher adaptability on environments through online learning. The results of comparison with Voting EM algorithm proposed by Cohen at el. confirm that the proposed method has the same performance in complete data set and higher performance in incomplete data set, comparing with Voting EM algorithm.

Online Adaptation of Continuous Density Hidden Markov Models Based on Speaker Space Model Evolution (화자공간모델 진화에 근거한 연속밀도 은닉 마코프모델의 온라인 적응)

  • Kim Dong Kook;Kim Young Joon;Kim Hyun Woo;Kim Nam Soo
    • Proceedings of the Acoustical Society of Korea Conference
    • /
    • spring
    • /
    • pp.69-72
    • /
    • 2002
  • 본 논문에서 화자공간모델 evolution에 기반한 continuous density hidden Markov model (CDHMM)의 online 적응에 대한 새로운 기법을 제안한다. 학습화자의 a priori knowledge을 나타내는 화자공간모델은 factor analysis (FA) 또는 probabilistic principal component analysis (PPCA)와 같은 은닉변수모델(latent variable model)에 의해 효과적으로 나타내어진다. 은닉 변수모델은 화자공간모델뿐아니라 CDHMM 파라메터의 ajoint prior분포를 표시함으로, maximum a posteriori(MAP)적응기법에 직접 적용되어진다. 화자공간모델의 hyperparameters와 CDHMM파라메터를 동시에 순차적으로 적응하기 위해 quasi-Bayes (QB)추정 기술에 기반한 online 적응기법을 제안한다. 연속숫자음 인식과 관련된 화자적응 실험을 통해 제안된 기법은 적은 적응데이터에서 좋은 성능을 나타내며, 데이터가 증가함에 따라 성능이 지속적으로 증가함을 보여준다.

  • PDF

An Adaptive PID Controller Design based on a Gradient Descent Learning (경사 감소 학습에 기초한 적응 PID 제어기 설계)

  • Park Jin-Hyun;Kim Hyun-Duck;Choi Young-Kiu
    • Journal of the Korea Institute of Information and Communication Engineering
    • /
    • v.10 no.2
    • /
    • pp.276-282
    • /
    • 2006
  • PID controller has been widely used in industry. Because it has 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 an adaptive PID controller based on a gradient descent learning. This algorithm has a simple structure like conventional PID controller and a robustness to system parameters variation and different velocity command. To verify performances of the proposed adaptive PID controller, the speed control of nonlinear DC motor is performed. The simulation results show that the proposed control systems are effective in tracking a command velocity under system parameters variation.

A Study on Fuzzy Rule Functional Verification for Threshold Value Prediction of Buffer in ATM Networks (ATM 망에서 버퍼의 임계값 예측을 위한 퍼지 규칙 기능 검증에 관한 연구)

  • 정동성;이용학
    • The Journal of Korean Institute of Communications and Information Sciences
    • /
    • v.29 no.8C
    • /
    • pp.1149-1158
    • /
    • 2004
  • In this thesis, we created a Fuzzy rule in a Fuzzy logic that are Fuzzy logic which is composed of linguistic rules and Fuzzy inference engine for effective traffic control in ATM networks. The parameters of the Fuzzy rules are adapted to minimize the given performance index in both cases. In other words, the difuzzification value controls the threshold in the buffer to arrival ratio to traffic priority (low or high) using fuzzy set theory for traffic connected after reasoning. Also, show experiment result about rule by MATLAB6.5 and on-line bulid-up to verify validity of created Fuzzy rule. As a result, we can verify that threshold value in buffer is efficiently controlled by the traffic arrival ratio.

A Study on Fuzzy Rule Functional Verification for Service ratio Prediction of Server in ATM Networks (ATM망에서 서버의 서비스율 예측을 위한 퍼지 규칙 기능 검증에 관한 연구)

  • 정동성;이용학
    • Journal of the Institute of Electronics Engineers of Korea TC
    • /
    • v.41 no.10
    • /
    • pp.69-77
    • /
    • 2004
  • In this thesis, we created a Fuzzy rule in a Fuzzy logic that are fuzzy logic which is composed of linguistic rules and Fuzzy inference engine for effective traffic control in ATM networks. The parameters of the Fuzzy rules are adapted to minimize the given performance index in both cases. In other words, the difuzzification value controls the service rate in the server to total traffic arrival ratio and buffer occupancy ratio using fuzzy set theory for traffic connected after reasoning. Also, show experiment result about rule by MATLAB6.5 and on-line bulid-up to verify validity of created Fuzzy rule. As a result, we can verify that service ratio in server is efficiently controlled by the total traffic arrival ratio and buffer occupancy ratio.