Aiming at the large spatial data sets whose qualities are complex and the situation that non - linearity , continuity and noises exist commonly , the spatial data mining method based on fuzzy neural network is put forward . an improved nearest neighboring clustering algorithm is used to construct the structure of fuzzy neural network , and thus fuzzy rules are extracted from large amounts of data to go on unsupervised learning , and only one dimension parameter needs to be adjusted by bp algorithm . so the method is speeded up , high efficient , accurate precision and has an extensive and promising application 针对庞大空间数据集性质复杂且非线性、持续性及噪音普遍存在的情况提出了基于模糊神经网络的空间数据挖掘方法,并采用一种改进的最近邻聚类算法用于构建模糊神经网络结构,可从大量的数据中自提取模糊规则进行无导师自学习,采用网络bp算法只调整一维参数,故计算速度较快并更好的保证了精度,经算例分析,证明了该方法快速、高效、精度高,具有广泛的应用前景。
The main factors of probabilistic neural network including the hidden neuron size , hidden central vector and the smoothing parameter , to influence the pnn classification , are analyzed ; the xor problem is implemented by using pnn . a new supervised learning algorithm for the pnn is developed : the learning vector quantization is employed to group training samples and the genetic algorithms ( ga ’ s ) is used for training the network ’ s smoothing parameters and hidden central vector for determining hidden neurons . simulations results show that , the advantage of our method in the classification accuracy is over other unsupervised learning algorithms for pnn 本文主要分析了pnn隐层神经元个数,隐中心矢量,平滑参数等要素对网络分类效果的影响,并用pnn实现了异或逻辑问题;提出了一种新的pnn有监督学习算法:用学习矢量量化对各类训练样本进行聚类,对平滑参数和距离各类模式中心最近的聚类点构造区域,并采用遗传算法在构造的区域内训练网络,实验表明:该算法在分类效果上优于其它pnn学习算法
One method was supervised recognition , which was to take advantage of some known information to determine a given sequence whether contained some specific functional elements ; the other way was unsupervised learning , which was to utilize some measures of comparability and some search algorithm to discovery some potential signals in biosequences 一种是有指导的识别方法,即利用已知的信息判读一段未知的序列中是否含有某种功能元件;另一种是无指导的学习方法,即利用一些相似性指标,通过搜索算法发现序列中可能蕴含的信号。
Since the instinct unsupervised learning of the rbf network and blind signal processing are in essence unsupervised learning procedures , therefore the algorithm based on rbf seems rational . 2 ) according to signals high order cumulant . bss problems are transformed into diagnolization of special matrix 2 )在研究随机过程理论的基础上,从信号的高阶累积量出发,将线性西安理工大学硕士学位论文混合盲分离问题转化为矩阵的对角化问题,大大简化了bss算法的复杂度。
The other is that when the extending areas of the samples overcross , wrong classification of the samples will occur . as for the first problem a genetic algorithm is used to improve the process of the best parameters " finding . and as for the latter a kind of improved hamming net which uses supervised and unsupervised learning method is employed 针对模糊hamming网络在应用中存在的参数调整效率低下以及难以保证参数最优的问题,提出了应用遗传算法进行参数调整的改进方法;针对该网络在样本离散范围发生交叠情况下导致归类错误的问题,研究了对于不同模式采用不同的警戒参数的有监督无监督混合学习的改进算法。
In machine learning, unsupervised learning refers to the problem of trying to find hidden structure in unlabeled data. Since the examples given to the learner are unlabeled, there is no error or reward signal to evaluate a potential solution.