Fundamental Research on Learning and Intelligence in System Control

系统控制中的学习与智能基础研究

基本信息

批准号：
02452180
负责人：
YAMAMOTO Yutaka
金额：
$ 3.26万
依托单位：
KYOTO UNIVERSITY
依托单位国家：
日本
项目类别：
Grant-in-Aid for General Scientific Research (B)
财政年份：
1990
资助国家：
日本
起止时间：
1990 至 1992
项目状态：
已结题

项目摘要

The focus of this research project is two fold: one is the general treatment of learning control scheme and the other is the study of learning mechanism of neural networks viewed from the system theoretic viewpoint. Needless to say, these two issues are mutually related.In the study of the general learning control scheme, results on stability conditions in the frequency domain, robust stability condition under plant perturbations are obtained. these results guaranteed that robustness analysis can be made for such learning schemes as modified repetitive control schemes based upon the methodology already employed for finite-dimensional systems.In relation to these, it is also clarified that the learning mechanism of neural networks and its application to control systems can be unified into the principle that the association of unorganized memories and the optimization in their respective parameter space. The notion of composite networks to be described below is the key to this development.In the study of neural networks, the fundamental standpoint of viewing networks as dynamical systems led to the following subjects: 1) derivation of a learning algorithm for general networks with feedback connections, 2) its application to pattern recognition, 3) its further generalization to composite networks, 4) application of more effective algorithms such as the conjugate gradient method, each leading to a satisfactory result. In particular, the composite networks enjoy such features as 1) making learning easier by decomposing the problem into smaller parts, 2) applicable to networks where teaching signals are implicit, and are expected to become more fundamental to various construction of neural networks.On the other hand, it has also become clear that more theoretical analysis is fairly difficult, partly due to the fundamental nonlinearity. More detailed research in this direction can be an open problem for the future.

该研究项目的重点是两个方面：一个是学习控制方案的一般治疗方法，另一个是从系统理论观点查看的神经网络的学习机制的研究。不用说，这两个问题是相互关联的。在一般学习控制方案的研究中，频域中的稳定性条件的结果获得了植物扰动下的稳健稳定性条件。这些结果可以确保可以根据已经用于有限维系统的方法进行修改的重复控制方案进行此类学习方案进行鲁棒性分析。在这些方法中，与这些方法相关的是，与这些方案相关，还澄清了神经网络的学习机制及其应用于其与其应用于其的学习机制控制系统可以统一为无组织记忆的关联及其各自参数空间中的优化的原则。要在下面描述的复合网络的概念是这种开发的关键。在神经网络的研究中，将网络视为动态系统的基本观点导致了以下主题：1）带有反馈的一般网络的学习算法的推导连接，2）将其应用于模式识别，3）其对复合网络的进一步概括，4）应用更有效的算法，例如共轭梯度方法，每种方法都会产生令人满意的结果。特别是，复合网络享有诸如1）通过将问题分解为较小的部分，2）适用于隐含教学信号的网络，并有望变得更加重要，并预计将变得更加重要另一方面，也很清楚，更多的理论分析是相当困难的，部分是由于基本的非线性。朝这个方向进行更详细的研究可能是未来的一个开放问题。