权益分类	功能权益	普通用户	{{item.name}}会员
{{category.name}}	{{benefitItem.name}}

Studies on Optimum Design method for multilayr Neural Net works with Minimum Network Sige

最小网络规模多层神经网络优化设计方法研究

基本信息

批准号：
07650422
负责人：
NAKAYAMA Kenji
金额：
$ 1.02万
依托单位：
Kanazawa University
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (C)
财政年份：
1995
资助国家：
日本
起止时间：
1995 至 1997
项目状态：
已结题

项目摘要

1. Pattern Classification by Multilayr Ne0ural NetworksIn the signal detection based on frequency components, when the number of the signal samples is limited, accurate detection by linear methods is difficult. The multilayr neural networks can provide high classification performance. The vectors of the signals, which have a small number samples or low SNR,are usually distributed randomly in the N dimensional space. Therefore, the boundary, which separate these vectors becomes very complicated. This can be done by using the nonlinearity of the neurons in the multilayr NNs.2. Selection of Minimum Training Data for GeneralizationA data selection method has been proposed, by which the data belong to the different classes and across over the boundary are selected. These data can guarantee generalization, that is the data, which were not used in the training can be effectively separated.3. Selection of Minimum Training Data for On-Line TrainingThe data are successively applied to the neural networks in the on-line applications. A method, which can select the useful data and hold the minimum number of the training data, has been proposed. Through several kinds of examples, the proposed method was confirmed to be useful.4.Optimization of Activation FunctionsThe network size required for some applications is highly dependent on the activation functions, that is nonlinear functions. A simultaneous learning method for both connection weights and activation functons has been proposed. The parity check problem, which is a difficult task for the multilayr neural networks, can be effectively solved using the minimum number of the hidden units.

1. 在基于频率分量的信号检测中，当信号样本数量有限时，用线性方法进行精确检测是困难的。多层神经网络具有较高的分类性能。样本数少或信噪比低的信号的向量通常在N维空间中随机分布。因此，分离这些向量的边界变得非常复杂。这可以通过利用多层神经网络中神经元的非线性来实现。泛化最小训练数据的选择提出了一种数据选择方法，该方法选择不同类别和跨边界的数据。这些数据可以保证泛化，即可以有效地分离未用于训练的数据。在线训练中最小训练数据的选择将数据依次应用于在线应用中的神经网络。提出了一种既能选择有用数据，又能保留最少训练数据的方法。通过几类算例，验证了所提方法的有效性。激活函数的优化某些应用程序所需的网络大小高度依赖于激活函数，即非线性函数。提出了一种连接权和激活函数同时学习的方法。奇偶校验问题是多层神经网络的一个难题，利用最小隐藏单元数可以有效地解决这一问题。