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

Mamalian-like neural networks for dynamic information processing and its learning algorithm

用于动态信息处理的类哺乳动物神经网络及其学习算法

基本信息

批准号：
04805032
负责人：
TAKAHASHI Haruhisa
金额：
$ 1.28万
依托单位：
The University of Electro-Communications
依托单位国家：
日本
项目类别：
Grant-in-Aid for General Scientific Research (C)
财政年份：
1992
资助国家：
日本
起止时间：
1992 至 1993
项目状态：
已结题

项目摘要

(1)It is mathematically investigated as to what kind of internal representations are separable by a single output unit of a three layr feednext neural network. A topologically described necessary and sufficient condition is shown for partitions of input spaces to be classified by the output unit. Then an efficient algorithm is proposed for checking if a given partition of the input space is resulted in linear separation at the output unit.(2)(3)These papers improves the sample complexity needed for reliable generalization in the PAC learnability in machine learning. By introducing an ill-posed learning algorithm which gives error worse over the candidates of network realizarions that are attained by minimizing empirical error, we can refine the order of the sample complexity, whereas the previous methods seek the uniform error over the whole configuration space. Essential VC dimension of concept classes, which is smaller than or equal to the number of modifiable system parameters, is introduced for calculating the generalization error instead of the traditional VC dimension analysis. Noisy learning is also treated.(4)In this paper we propose a very simple recurrent neural network(VSRN)architecture which is a three-layr network and contains only self-loop recurrent connections in the hidden layr. The role of the recurrent connection is explained by the network dynamic and its function will be acquired by learning from finite examples like a mamalian action. Through the learning process some characteristic functions observed in the mamalian auditory systems are found automatically acquired by the network. These contain on-neuron, off-neuron and on-off-neuron. This architecture can perform phoneme spotting in real time by utilizing these characteristic functions. Some simulation experiments are done to investigate the recognition performance.

(1)从数学上研究了三层FeedNext神经网络的单个输出单元可以分离什么样的内部表示。给出了输入空间划分按输出单位分类的一个拓扑学描述的充要条件。然后提出了一种有效的算法来检验给定的输入空间划分是否导致输出单元的线性分离。(2)(3)改进了机器学习中PAC可学习性中可靠泛化所需的样本复杂性。通过引入一种不适定的学习算法，使得误差比通过最小化经验误差得到的网络实现候选更差，从而改进了样本复杂性的顺序，而以前的方法是在整个配置空间上寻求一致的误差。为了计算泛化误差，引入概念类的本质VC维来代替传统的VC维来计算泛化误差。本文提出了一种非常简单的递归神经网络(VSRN)结构，它是一个三层网络，隐层只包含自环递归连接。循环连接的作用由网络动力学解释，其功能将通过从有限的例子(如哺乳动物动作)中学习来获得。通过学习过程，网络可以自动获取哺乳动物听觉系统中观察到的一些特征函数。这些神经元包括ON神经元、OFF神经元和ON OFF神经元。该体系结构可以利用这些特征功能来实时地进行音素检测。通过仿真实验研究了该算法的识别性能。