arXivDaily arXiv每日学术速递 周一至周五更新
arXiv 0712.0938cs.LGcs.AIcs.NE
收藏

基于镜像神经网络数据简化的无监督学习自动模式分类

Automatic Pattern Classification by Unsupervised Learning Using Dimensionality Reduction of Data with Mirroring Neural Networks

College of Engineering, Osmania University(奥斯马尼亚大学工程学院);Altech Imaging & Computing(阿尔泰克成像与计算公司);Sreenidhi Institute of Science and Technology(斯雷尼迪科技学院)

Dasika Ratna Deepthi, G. R. Aditya Krishna, K. Eswaran

摘要:

提出了一种基于多层镜像神经网络和Forgy聚类算法的无监督学习方法。多层镜像神经网络是一种神经网络,它可以用广义数据输入(不同类别的图像模式)进行训练,以执行非线性降维,并使用Forgy算法将所得的低维代码用于无监督模式分类。通过调整非线性激活函数(修改的S形函数)并将权重和偏置项初始化为小的随机值,启动输入模式的镜像。在训练中,权重和偏置项以这样的方式改变,即通过反向传播误差,在输出处再现所呈现的输入。镜像神经网络能够在很大程度上减少输入向量(约为原始大小的1/30),并且还能够从该减少的代码单元在输出层重构输入模式。从该网络中提取的特征集(中央隐藏层的输出)被馈送到Forgy算法,该算法将输入数据模式分类为可区分的类别。在Forgy算法的实现中,初始种子点的选择方式是,它们足够远,可以完美地分为不同的类别。因此,本文提出并论证了一种新的无监督学习方法。该方法在应用于不同图像模式的分类时,给出了令人印象深刻的结果。

英文摘要:

This paper proposes an unsupervised learning technique by using Multi-layer Mirroring Neural Network and Forgy's clustering algorithm. Multi-layer Mirroring Neural Network is a neural network that can be trained with generalized data inputs (different categories of image patterns) to perform non-linear dimensionality reduction and the resultant low-dimensional code is used for unsupervised pattern classification using Forgy's algorithm. By adapting the non-linear activation function (modified sigmoidal function) and initializing the weights and bias terms to small random values, mirroring of the input pattern is initiated. In training, the weights and bias terms are changed in such a way that the input presented is reproduced at the output by back propagating the error. The mirroring neural network is capable of reducing the input vector to a great degree (approximately 1/30th the original size) and also able to reconstruct the input pattern at the output layer from this reduced code units. The feature set (output of central hidden layer) extracted from this network is fed to Forgy's algorithm, which classify input data patterns into distinguishable classes. In the implementation of Forgy's algorithm, initial seed points are selected in such a way that they are distant enough to be perfectly grouped into different categories. Thus a new method of unsupervised learning is formulated and demonstrated in this paper. This method gave impressive results when applied to classification of different image patterns.

机构、总结、中文摘要均由AI分析而来,可能存在错误,请以论文正文为准。

↑