竞争学习

  • 网络Competitive Learning;competition learning;fscl
竞争学习竞争学习
  1. FNN上的竞争学习及混合学习方法

    Competition competitive learning and mixed learning methods in FNN

  2. 基于模糊竞争学习和UD分解的模糊建模

    Fuzzy modeling based on fuzzy competitive learning and matrix UD decomposition

  3. HS-K-WTA-2以竞争学习算法为基础。HS-K-WTA-2能够从任何一个数集中识别出K个较大的数,或K个较小的数。

    HS-K-WTA-2 can identify the larger elements ( or smaller ones ) in a data set .

  4. 本文构造了径向基函数(RBF)神经网络的一类软竞争学习算法(SCLA)。

    In this paper , the soft competition learning algorithms ( SCLA ) of RBF neural networks are designed .

  5. 利用基于竞争学习理论的Kohonen自组织网络模型,设计了一种新的变压器故障诊断方案。

    Based on Kohonen network model , a new method used for power transformer fault diagnosis is presented in this paper .

  6. 首先阐述了CMAC神经网络的原理、结构和学习算法,提出了一种新的采用竞争学习原理的非等距自适应量化算法。

    We first discuss the structure and principle of the CMAC neural network . Using competitive learning , we develop a new adaptive quantization algorithm .

  7. 介绍了利用GAL算法对装备产生的声音信号进行处理,改进完善了基于竞争学习的GAL神经网络。

    In this paper , introduces a new method of GAL algorithm that can process the sound signal of armored vehicle and improves GAL network based on self-learning .

  8. 首先,利用竞争学习算法对输入空间进行聚类,基于此结果,借助于模糊C均值聚类算法进一步优化聚类结果,提取T-S模糊模型的规则前件隶属函数参数。

    Firstly , the input space is clustered by competitive learning algorithm , and based on the result , the clustering results are optimized by fuzzy C-means clustering algorithm , then the membership function of the antecedent fuzzy sets is obtained .

  9. 竞争学习网络与Kohonen神经网络相比,由于不考虑邻域神经元,其网络结构相对简单。

    In comparison with the Kohonen neural networks , the structure of the compete study networks is relatively simple because it does not consider neighboring neural units .

  10. 本文提出了一种用神经网络技术学习模糊分类规则的算法&有导师共振竞争学习算法(SRCL)。

    This paper describes a learning method of fuzzy classification rules with neural networks - supervised resonance competing learning ( SRCL ) .

  11. 采用GA寻优与BP算法学习模糊神经网络参数,通过竞争学习算法从样本数据中获取模糊控制规则,并与专家经验有机结合,弥补了各自的不足。

    The parameters of fuzzy neural network are learned by GA optimization and BP algorithm . Using competitive learning algorithm , fuzzy rules can be obtained from sample data and the learned rules are properly combined with experts ' experiences for complementing the deficiency of each of them .

  12. 基于群体的增量学习算法(PBIL)是一种将遗传算法和竞争学习相结合的新型进化优化算法。

    The Population-Based Incremental Learning ( PBIL ) is a novel evolutionary algorithm combined the mechanisms of the Genetic Algorithms with competitive learning .

  13. 本文根据[1]所提出的FNN结构,首先讨论它的竞争学习方法,它除了可以应用到FNN上的输入均值和输出权重的调整外,还可以用于实现网络连线的裁剪。

    Based on reference [ 1 ] , this paper gives the method of competitive learning in FNN , which can be applied not only to adjusting input-means and output-weights , but also to cutting the links among nodes in FNN .

  14. 根据等失真(Equidistortion)理论提出了一种基于改进的自组织特征映射(SOFM)神经网络的矢量量化方法,该算法将失真敏感机制引入神经网络的竞争学习过程。

    A codebook designing algorithm of vector quantization based on modified self-organizing feature maps ( SOFM ) was proposed . Distortion sensitive was inducted into competitive learning of neural network .

  15. 该文通过熵方法和竞争学习算法对输入空间进行聚类,利用递推最小二乘辨识算法(RLS)确定模型的结论参数,实现了蒸发器动态过程数学模型的在线模糊辨识。

    This paper partitions the input data into some clusters by entropy method and competitive learning algorithm , then the on-line fuzzy identification of dynamic process mathematical model of evaporator is achieved by utilizing ultimate parameter which is ascertained by the recursive least-square ( RLS ) .

  16. 该系统用数值化的模糊联想记忆(FAM)规则表示专家的领域知识并进行模糊推理,同时采用神经网络的微分竞争学习算法(DCL)实现规则的自适应生成。

    Numerical fuzzy associative memory ( FAM ) rules are applied to the expression of human expert knowledge and fuzzy inference . A differential competitive learning approach in the neural network is adopted to adaptively generate FAM rules and learn new knowledge .

  17. 提出了基于模糊协方差的自适应聚类神经网络(FCACNN)算法,结合神经网络的竞争学习和模糊协方差的相似性度量,通过迭代合并方法实现了稳健的多特征聚类处理。

    Fuzzy covariance-based adaptive clustering neural networks ( FCACNN ) is presented . It combines the competitive learning of the neural networks and the distance measurement of the fuzzy covariance clustering algorithm to cluster steadily by combining the resemble clusters iteratively .

  18. 基于竞争学习的神经网络自适应模糊控制

    Adaptive fuzzy control based on the competitive - study neural network

  19. 基于内容的条件类熵约束软竞争学习图像分类器

    Content-Based Image Classifier Realized by Conditional Class-Entropy Constrained Soft Competitive Learning

  20. 基于模糊竞争学习的模糊模型一体化辨识

    An integrated identification of fuzzy model based on fuzzy competitive learning

  21. 加强学生的竞争学习,培养竞争能力;

    Encourage competition between the students to improve their competence ;

  22. 基于遗传算法与小波变换的竞争学习系统

    Competitive Learning System on the Basis of Genetic Algorithms and Wavelets Transforms

  23. 竞争学习神经网络的译码功能研究

    A Tentative Investigation of the Error-correcting Function of Competitive Learning Neural Network

  24. 熵约束广义学习矢量量化神经网络和软竞争学习算法

    Competition entropy-constrained generalized learning vector quantization neural network and soft competitive learning algorithm

  25. 基于小波变换和误差竞争学习的矢量量化

    Vector Quantization Based on Wavelet-Transform and Distortion Competitive Learning

  26. 其次由竞争学习算法完成模糊规则确定;

    Secondly , the compete algorithm is used to determine the fuzzy rules ;

  27. 聚类分析中竞争学习的一种新算法

    A new competitive learning algorithm for clustering analysis

  28. 次胜者受罚竞争学习规则可以进行有效的聚类并自动确定适当的聚类数目。

    Rival Penalized Competitive Learning can cluster and get a proper cluster number automatically .

  29. 因此可以利用它稳定机制和竞争学习的优点来进行车辆的分类识别。

    So we can use its stable merits and competitive learning to classify features .

  30. 利用竞争学习对输入空间自适应聚类;

    The self-adaptive category gathering is operated on input space by using competition learning ;