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

DEVELOPMENT OF SELF-ORGANIZING LEARNING NETWORK BY USING PULSE MODULATING DIGITAL CIRCUITS.

使用脉冲调制数字电路开发自组织学习网络。

基本信息

批准号：
10480065
负责人：
HIRAI Yuzo
金额：
$ 3.2万
依托单位：
University of Tsukuba
依托单位国家：
日本
项目类别：
Grant-in-Aid for Scientific Research (B)
财政年份：
1998
资助国家：
日本
起止时间：
1998 至 1999
项目状态：
已结题

项目摘要

A learning network which can perform PCA (Principal Component Analysis) was designed by using PDM (Pulse Density Modulating) digital circuits and fabricated in a FPGA (Field Programmable Gate Array). It was verified that the circuit could learn principal components in an input signal real-time. The discrete PCA learning algorithm proposed by Sanger was changed into a continuous form and the circuit solved a set of learning differential equations in a parallel and continuous manner.Experiment was performed by using a small circuit with two microphone inputs and two speaker outputs. The following results were obtained :a) After learning sound appeared from only one speaker, which extracted a principal component, when a sound source was presented in front of the microphones.b) The sets of connection weights from the two microphones to the principal speaker converged to a principal vector which directed to the sound source.c) When the sound source moved, the weight vector continuously tracked the sound direction in real-time.

采用脉冲密度调制（PDM）数字电路设计了一个可执行主成分分析（PCA）的学习网络，并在现场可编程门阵列（FPGA）上实现。实验证明，该电路能够实时学习输入信号中的主成分。将Sanger提出的离散PCA学习算法转化为连续形式，电路以并行连续的方式求解一组学习微分方程。实验采用了一个带有两个麦克风输入和两个扬声器输出的小电路。得到的结果如下：a)学习后，当麦克风前有声源时，只出现一个扬声器的声音，提取一个主成分。b)两个传声器到主扬声器的连接权值集合收敛为指向声源的主向量。c)当声源移动时，权值向量实时连续跟踪声音方向。