Description: This book is about the use of artificial neural networks for supervised learning problems. Many such problems occur in practical applications of artificial neural networks. For example, a neural network might be used as a component of a face recognition system for a security appli-
cation. After seeing a number of images of legitimate users' faces, the network needs to determine accurately whether a new image corresponds to the face of a legitimate user or an imposter. In other applications, such as the prediction of future price of shares on the stock exchange, we may require a neural network to model the relationship between a pattern and a real-valued quantity. Platform: |
Size: 20091030 |
Author:kj5566 |
Hits:
Description: 人脸识别的经典算法的完美结合，PAC与FISHER算法C++实现，首先通过PCA进行维数约简，然后通过FISHER进行最有利的方向投影。识别效率是所有监督学习的上限。-Face Recognition Algorithm for the perfect combination of classic, PAC and FISHER algorithm C++ Realize, first of all carried out through the PCA dimension reduction, and then through to the most favorable FISHER projection direction. Recognition efficiency is all supervised learning ceiling. Platform: |
Size: 758784 |
Author:NEO |
Hits:
Description: 本代码实现基于成对约束的半监督图嵌入算法-Following the intuition that the image variation of
faces can be effectively modeled by low dimensional
linear spaces, we propose a novel linear subspace
learning method for face analysis in the framework of
graph embedding model, called Semi-supervised
Graph Embedding (SGE). This algorithm builds an
adjacency graph which can best respect the geometry
structure inferred from the must-link pairwise
constraints, which specify a pair of instances belong to
the same class. The projections are obtained by
preserving such a graph structure. Using the notion of
graph Laplacian, SGE has a closed solution of an
eigen-problem of some specific Laplacian matrix and
therefore it is quite efficient. Experimental results on
Yale standard face database demonstrate the
effectiveness of our proposed algorithm. Platform: |
Size: 2048 |
Author:刘国胜 |
Hits:
Description: 综合了主动学习和半监督学习的多项算法，很有价值的学习资料-Combination of active learning and a number of semi-supervised learning algorithm, learning valuable information Platform: |
Size: 2048 |
Author:苏航 |
Hits:
Description: 面对模式分析、数据挖掘中海量数据,降维算法已经成为科学研究人员最为
强有力的工具.对降维算法的研究具有很高的学术价值和应用潜力.本文较为详
细的回顾了现有的降维算法,以及他们在模式分析中的应用.在此基础上,着眼于
提高嵌入空间的不同类别的样本之间的距离,我们提出了两种有监督情形下的流
形学习算法.模拟和实际数据都显示了有监督流形学习算法的良好的性能.-Face pattern analysis, data mining massive data, dimension reduction algorithm has become the most powerful scientific tool for staff. Dimensionality reduction algorithm of high academic value and potential applications of this paper a more detailed review of the existing dimensionality reduction algorithms and their applications in pattern analysis. On this basis, focusing on improving the embedding space, different types of distance between samples, we proposed two kinds of cases supervised manifold learning algorithm simulation and actual data have shown a supervised manifold learning algorithm good performance. Platform: |
Size: 3636224 |
Author:罗朝辉 |
Hits:
Description: LVQ即学习向量量化神经网络是一种用于训练竞争层的有监督学习方法神经网络，在模式识别和优化领域有着广泛的应用。本课题要求使用LVQ神经网络训练人脸的特征数据，得到模型对任一人脸图像的朝向进行识别。-Learning Vector Quantization LVQ neural network that is used to train competitive layer neural network supervised learning methods in the field of pattern recognition and optimization has been widely used. This problem requires the use of trained LVQ network facial feature data, the model for any one person to identify the orientation of the face image. Platform: |
Size: 3607552 |
Author:吴军 |
Hits:
Description: 人脸识别是一个有监督学习过程，首先利用训练集构造一个人脸模型，然后将测试集与训练集进行匹配，找到与之对应的训练集头像。最容易的方式是直接利用欧式距离计算测试集的每一幅图像与训练集的每一幅图像的距离，然后选择距离最近的图像作为识别的结果。这种直接计算距离的方式直观，但是有一个非常大的缺陷—计算量太大。如果每幅图像大小为100*100，训练集大小1000，则识别测试集中的一幅图像就需要1000*100*100的计算量，当测试集很大时，识别速度非常缓慢。(Face recognition is a supervised learning process. Firstly, a face model is constructed by training set, and then the test set is matched with the training set to find the corresponding training set head. The easiest way is to directly use the Euclidean distance to compute the distance between each image of the test set and each image of the training set, and then select the nearest image as the result of recognition. This method of calculating distances directly is intuitive, but there is a very big flaw - too much computation. If the size of each image is 100*100, and the training set size is 1000, then it is necessary to recognize an image in the test set, and the computation amount of 1000*100*100 is required. When the test set is large, the recognition speed is very slow.) Platform: |
Size: 11449344 |
Author:浏览量
|
Hits:
Description: 人脸识别是一个有监督学习过程，首先利用训练集构造一个人脸模型，然后将测试集与训练集进行匹配，找到与之对应的训练集头像。最容易的方式是直接利用欧式距离计算测试集的每一幅图像与训练集的每一幅图像的距离，然后选择距离最近的图像作为识别的结果。(Face recognition is a supervised learning process. Firstly, a face model is constructed by training set, and then the test set is matched with the training set to find the corresponding training set head. The easiest way is to directly use the Euclidean distance to compute the distance between each image of the test set and each image of the training set, and then select the nearest image as the result of recognition. This method of calculating distances directly is intuitive, but there is a very big flaw - too much computation.) Platform: |
Size: 8253440 |
Author:浏览量
|
Hits:
Search - Supervised Learning face