Synthesis of Incremental Learning Architecture of Competitive Associative Neural Nets and Their Application to Control

竞争联想神经网络增量学习架构的综合及其在控制中的应用

• 批准号: 12680389
• 负责人: KUROGI Shuichi
• 金额: $ 2.11万
• 依托单位: Kyushu Institute of Technology
• 依托单位国家: 日本
• 项目类别: Grant-in-Aid for Scientific Research (C)
• 财政年份: 2000
• 资助国家: 日本
• 起止时间: 2000 至 2002
• 项目状态: 已结题
• 来源: https://kaken.nii.ac.jp/grant/KAKENHI-PROJECT-12680389/
• 关键词: competitive associative nets; competitive learning; associative memory; temperature control; silicon wafers; RCA cleaning system

In this research, we have investigated the competitive neural nets (CANs) from the following facets, and obtained successful results.1. Synthesis and analysis of efficient incremental learning methods:As a result of this research, we have fond out asymptotic optimality of the CANs, and synthesized incremental learning methods. From comparative study with the conventional BPN (back-propagation nets), RBFN (radial basis function nets) and SVR (support vector regression) which is famous for its very good performance in nonlinear regression, the CANs with the new learning methods developed in this research show the best performance in nonlinear function approximation for various nonlinear functions even when the data involves noise. The CANs with the new learning methods are also applied to rainfall estimation, speech recognition, nonlinear chaos prediction, etc. and we obtained very good results. Especially, in a rainfall estimation contest held by IEICE (Institution of electronics, infor … More mation and communication engineers), our result using the CAN have honored the second prize.2. Application of the nets to model switching control:We have applied the above methods to temperature control of RCA solutions for cleaning silicon wafers. The actual RCA cleaning system is dangerous and unstable because the solutions are highly concentrated sulfuric acid (H2SO4), hydrogen peroxide (H2O2), etc., so that it is hard to obtain good repeatability in verification experiments of the control. We in this research have developed the thermal model of the RCA cleaning system, which is done for the first time in the world, and utilized in a lot of numerical experiments where the model switching controller using the CANs is applied the numerical model of the RCA cleaning system for estimating the best control parameter values, and the controller finally are the real RCA system. We have also developed a real time simulator of the RCA system for comparative studies with the commercial controllers whose control algorithms are not open, and we have verified the efficiency of the present controller.In this research, especially in modeling the RCA cleaning system, in the real experiments, and in the development of the real time simulator, a lot of helps of Komatsu Electronics Inc. have been very important. Less

在本研究中，我们从以下几个方面对竞争神经网络进行了研究，并取得了成功的结果.高效增量学习方法的综合与分析：通过研究，我们发现了网络的渐近最优性，并综合了增量学习方法。通过与传统的BPN（back-propagation nets）、RBFN（radial basis function nets）以及在非线性回归方面表现优异的SVR（support vector regression）等算法的比较研究表明，采用本研究开发的新学习方法的CAN在各种非线性函数的逼近方面表现出了最佳的性能，即使在数据包含噪声的情况下也是如此。将这种新的学习方法应用于雨量估计、语音识别、非线性混沌预测等方面，取得了很好的效果。特别是，在IEICE（Institution of electronics，infor ...更多信息 信息和通信工程师），我们使用CAN的成果荣获二等奖。网络模型切换控制的应用：我们已经将上述方法应用于清洗硅片的RCA溶液的温度控制。实际的RCA清洗系统是危险且不稳定的，因为溶液是高浓度硫酸（H2SO 4）、过氧化氢（H2 O2）等，从而在控制的验证实验中难以获得良好的重复性。在本研究中，我们开发了RCA清洗系统的热模型，这是世界上第一次，并在大量的数值实验中使用，其中使用CAN的模型切换控制器应用于RCA清洗系统的数值模型，以估计最佳的控制参数值，并且控制器最终是真实的RCA系统。我们还开发了一个RCA系统的真实的时间模拟器，与控制算法不开放的商用控制器进行了比较研究，并验证了本控制器的有效性。在本研究中，特别是在RCA清洗系统的建模、真实的实验和真实的时间模拟器的开发中，小松电子公司提供了大量的帮助。都非常重要少

项目成果

S.Kurogi and T.Nishida.: "Competitive learning using gradient and reintalization methods for adaptive vector quantization"Proceedings of the IEEE International Workshop on Neural Networks for Signal Processing. 281-288 (2000)

S.Kurogi 和 T.Nishida.：“使用自适应矢量量化的梯度和重新初始化方法进行竞争性学习”IEEE 国际信号处理神经网络研讨会论文集。

T.Nishida., S.Kurogi., and T.Saeki.: "An analysis of competitive and reinitialization learning for adaptive vector quantization"Proceeding of International Joint Conference on Neural Networks. 978-983 (2001)

T.Nishida.、S.Kurogi. 和 T.Saeki.：“自适应矢量量化的竞争性和重新初始化学习的分析”国际神经网络联合会议论文集。

Shuichi Kurogi: "Asymptotic optimality of competitive associative nets for their learning in function approximation"Proceedings of International on Neural Information Processing. 507-511 (2002)

Shuichi Kurogi：“竞争关联网络在函数逼近中学习的渐近最优性”国际神经信息处理学报。

Shuichi Kurogi: "Asymptotic minimization of the Approximation error of competitive associative nets and its application to temperature control of RCA cleaning solutions"Proceedings of International Conference on Neural Information Processing. 1900-1904 (2

Shuichi Kurogi：“竞争关联网络近似误差的渐近最小化及其在 RCA 清洁解决方案温度控制中的应用”神经信息处理国际会议论文集。

黒木秀一, 上野貴雅, 田中健吾: "競合連想ネットの漸近最適性とカオス時系列予測への応用"日本神経回路学会全国大会論文集. 295-298 (2001)

Shuichi Kuroki、Takamasa Ueno、Kengo Tanaka：“竞争关联网络的渐近最优性及其在混沌时间序列预测中的应用”日本神经网络学会全国会议论文集 295-298 (2001)。