Description: 《Neural Networks for Text-to-Speech Phoneme Recognition》This paper presents two different artificial neural network approaches for phoneme recognition for text-to-speech applications: Staged Backpropagation Neural Networks and Self-Organizing Maps.- Neural Networks for Text-to-Speech Phoneme Recognition This paper presents two different artificial neural network approaches for phoneme recognition for text-to-speech applications: Staged Backpropagation Neural Networks and Self-Organizing Maps. Platform: |
Size: 722944 |
Author:付诗 |
Hits:
Description: Basic library that implements Kohonen s SOM and its learning. Lanuage: C# (.Net 3.5 Framework) Platform: |
Size: 35840 |
Author:Larrr |
Hits:
Description: Thesis from the Charles University (Prague) about Kononen s Self-organizing maps. In English. Platform: |
Size: 8182784 |
Author:Larrr |
Hits:
Description: It s toolbox in determining the crime pattern analysis using SOM (Self-Organizing Maps). It s using SOM clusters and K-means clusters. Platform: |
Size: 434176 |
Author:Najihah |
Hits:
Description: Kohonen article of self-organizing maps, published in 1982 in IEEE. It contain general ideas about self-organizing neural networks. Platform: |
Size: 1497088 |
Author:luxury_x |
Hits:
Description: Neural Network Based Clustering
using Self Organizing Map (SOM) in Excel
Here is a small tool in Excel using which you can find clusters in your data set. The tool uses Self Organizing Maps (SOM) - originally proposed by T.Kohonen as the method for clustering.
* Neural Network based Clustering tool in Excel (209 KB in Zipped format. 947 KB when unzipped.)
Inside the downloaded zip file, you will find the Excel file containing the application. Before running it, I suggest that you go through the ReadMe worksheet. It contains brief instructions on how to run the tool.
If you are interested in building Prediction and Classification models in Excel using Feedforward-Backpropagation Neural Network, here are two small Excel based tools for you. Also, if you are interested in Tree based Classification models, here is a Tree based classifier in Excel.
-Neural Network Based Clustering
using Self Organizing Map (SOM) in Excel
Here is a small tool in Excel using which you can find clusters in your data set. The tool uses Self Organizing Maps (SOM)- originally proposed by T.Kohonen as the method for clustering.
* Neural Network based Clustering tool in Excel (209 KB in Zipped format. 947 KB when unzipped.)
Inside the downloaded zip file, you will find the Excel file containing the application. Before running it, I suggest that you go through the ReadMe worksheet. It contains brief instructions on how to run the tool.
If you are interested in building Prediction and Classification models in Excel using Feedforward-Backpropagation Neural Network, here are two small Excel based tools for you. Also, if you are interested in Tree based Classification models, here is a Tree based classifier in Excel.
Platform: |
Size: 214016 |
Author:Jessie |
Hits:
Description: this algorithm in matla help to apply som self organizing maps-this algorithm in matla help to apply som self organizing maps Platform: |
Size: 638976 |
Author:tito |
Hits:
Description: 对图像进行了预处理，同时确定了图像的分类数，对图像进行了基于自组织特征映射的图像聚类处理。-Of the image of the pre-processing, while identifying the classification of the image the number of pairs of images based on self-organizing maps clustering image processing. Platform: |
Size: 3072 |
Author:lmj |
Hits:
Description: SOM神经网络（自组织特征映射神经网络）是一种无导师神经网路。网络的拓扑结构是由一个输入层与一个输出层构成。输入层的节点数即为输入样本的维数，其中每一节点代表输入样本中的一个分量。输出层节点排列结构是二维阵列。输入层X中的每个节点均与输出层Y每个神经元节点通过一权值(权矢量为W)相连接，这样每个输出层节点均对应于一个连接权矢量。
自组织特征映射的基本原理是，当某类模式输入时，其输出层某一节点得到最大刺激而获胜，获胜节点周围的一些节点因侧向作用也受到较大刺激。这时网络进行一次学习操作，获胜节点及其周围节点的连接权矢量向输入模式的方向作相应的修正。当输入模式类别发生变化时，二维平面上的获胜节点也从原来节点转移到其它节点。这样，网络通过自组织方式用大量训练样本数据来调整网络的连接权值，最后使得网络输出层特征图能够反映样本数据的分布情况。根据SOM网络的输出状况，不仅能判断输入模式所属的类别，使输出节点代表某类模式，而且能够得到整个数据区域的分布情况，即从样本数据得到所有数据的分布特征。 -SOM neural network (self-organizing feature map neural network) is an unsupervised neural network. Network topology is an input layer and an output layer. Input layer nodes is the input dimension of the sample, each node represents a component input samples. Output layer nodes are arranged in two-dimensional array structure. X in the input layer and output layer each node of each neuron node Y by a weight (the weight vector as W) is connected, so that each output layer corresponds to a connection node of the right vector.
Self-organizing feature maps of the basic principle is, when each category of inputs into the model, its output layer one node get the maximum boost and win, Huoshengjiedian around Yixiejiedian Yin Zuo Yong Ye Shoudaojiaotai lateral stimulation. Then a learning network operation, the winner node and surrounding nodes in the right direction vector to the input mode to make consequential amendments. When the input mode type changes, the two-dimensional plane of the wi Platform: |
Size: 47104 |
Author:leidan |
Hits:
Description: 自组织特征映射模型(Self-Organizing feature Map)，认为一个神经网络接受外界输入模式时，将会分为不同的区域，各区域对输入模式具有不同的响应特征，同时这一过程是自动完成的。各神经元的连接权值具有一定的分布。最邻近的神经元互相刺激，而较远的神经元则相互抑制，更远一些的则具有较弱的刺激作用。自组织特征映射法是一种无教师的聚类方法。-Self-organizing maps model (Self-Organizing feature Map), that a neural network to accept outside input mode, will be divided into different regions, the regional input modes have different response characteristics, while the process is done automatically . The connection weights of neurons with a certain distribution. Nearest neurons stimulate each other, while distant neurons are mutually inhibitory, with a further some of the weaker stimulus. Self-organizing feature map method is a clustering method without teachers. Platform: |
Size: 1024 |
Author:yyt |
Hits:
Search - self organizing maps