分段式过程神经元网络

研究分段式过程神经网络模型及其学习算法.在过程神经元网络基础上提出分段式过程神经网络模型,并给出在已知和未知各阶段期望输出两种情况下的学习算法,目的是模拟分段目标规划和评判系统.最后给出大学生综合评价系统的应用实例,模拟仿真结果说明模型和算法是有效的.     

基于VC++(MFC)的并行神经 网络学习系统的设计及实现

介绍了一个以基于BP模型的并行神经网络(PNN)模型为基础 ,利用VC++(MFC)开发的并行神经网络学习系统的具体实现过程。给出了实现思路、程序框 架等。     

用过程神经网络和遗传算法实现系统逆向求解

对于多输入多输出系统,针对如何根据系统模型和期望输出反求系统输入的问题,本文提出了一种基于过程神经网络和遗传算法相结合的方法.首先根据实际系统的领域知识和学习样本集,建立满足系统实际输入输出映射关系的正向过程神经网络.然后按照系统在过程区间的某一期望输出,用过程神经网络的输出误差构造适应度函数,用遗传算法逆向确定系统的过程输入信号,使该输入信号满足已建立的正向过程映射关系,从而完成系统的逆向过程控制.文中给出了具体的实现算法并给出了此方法的一个应用实例.     

一类用于连续过程逼近的过程神经元网络及其应用

针对实际系统的输入输出是与时间有关的连续过程,提出了一类用于连续过程逼近的过程神经元网络模型.模型利用神经网络所具有的非线性映射能力,实现系统输入输出之间的连续映射关系.考虑过程神经网络计算的复杂性,在输入空间中选择一组函数正交基,将输入函数和网络权函数表示为该组正交基的展开形式,利用基函数的正交性,简化过程神经元计算.文中给出了学习算法,并以油藏开发三次采油过程模.     

连续小波过程神经网络及其仿真研究

在小波分析和过程神经网络理论的基础上，提出了连续小波过程神经网络模型，其隐层为过程神经元，隐层激活函数采用小波函数．该网络结合了小波变换良好的时一频局域化性质及过程神经网络可以处理连续输入信号的特点，因而学习能力强，精度高．给出了小波过程神经网络学习算法，并以航空发动机滑油系统状态监测为例，分别利用传统BP网络和小波过程神经网络进行预测．结果表明，小波过程神经网络收敛速度快，精度高，优于BP网络的预测能力，同时也为航空发动机滑油系统状态监测问题提供了一种有效的方法．     

基于时变神经网络的非线性时变系统建模

提出时变神经网络模型,用以逼近未知非线性时变映射,实现非线性时变系统建模.将时变神经网络的权值学习作为时变系统的时变参数估计问题,并基于迭代学习机制,给出在同一时刻沿迭代轴训练网络权值的迭代学习最小二乘算法.理论上证明了该算法的全局收敛性.给出的数值算例表明所提算法在非线性时变系统建模方面的有效性.     

一种模糊推理过程神经网络及其应用研究

针对带有过程性模糊信息或动态领域规则的时变信息处理问题,提出一种模糊推理过程神经网络.该模型将模糊过程推理规则与数值型过程神经网络的动态信息处理机制相结合,将推理规则表示为过程神经元.利用过程神经网络的学习性质来实现对过程性定量与定性混合信息的自适应处理.分析了模糊推理过程神经网络的信息处理机制,并给出了相应的学习算法.以抽油机平衡诊断为例,实验结果验证了所提出模型和算法的有效性.     

一种基于过程神经网络的动态系统控制信号求解模型和算法

针对非线性动态系统控制问题,提出了一种基于过程神经网络的控制信号求解模型和算法。利用过程神经网络对动态系统时变输入/输出信号的非线性映射机制和对系统过程模态特征的自适应提取能力,建立基于过程神经网络的辨识模型;然后根据所建立的辨识模型、系统控制结构和状态参数之间的关系,构建可满足系统信息传递约束关系的控制信号求解模型。分析了过程神经网络控制模型的信息处理机制,给出了基于GA与LMS相结合的优化求解算法,实验结果验证了模型和算法的有效性。     

基于LSFD算法的小波模糊神经网络的研究与应用

利用小波变换的多分辨率特性构造小波模糊神经网络模型,并应用在非线性系统的辨识上.在参数学习上,给出了模糊微分与李亚普诺夫稳定相结合的新算法—LSFD算法,并与梯度下降法进行了对比.通过仿真,结果表明小波模糊神经网络模型与模糊神经网络、模糊小波神经网络、小波神经网络和神经网络等模型相比,其性能指标最小,收敛速度更快,更加准确.     

一类递归RBF神经网络模型的稳定性讨论

在径向基函数神经网络（RBFNN）和递归神经网络（RNN）的基础上,提出了一类新的递归径向基函数神经网络（RRBFNN）模型,它具有两种网络模型的优点。文中对它的渐近稳定性和学习算法进行了研究,并给出相关的定理和公式。仿真结果表明了该神经网络模型在控制不稳定非线性系统（如小车－倒摆系统）具有巨大潜力。     

一种形式化的学习过程建模

目前对E-learning技术进行深入的研究对于丰富我国教育方式和提高总体教育水平有着重要的意义。学习过程的建模则是为实现学习管理系统,将E-learning的相关理念运用于实际,打下坚实的理论基础。本文首先介绍了学习设计理念以及Petri网的概念。其次,依次描述了学习活动和活动构件、技能、学习过程的建模过程,并在在此基础上补充了活动结构的概念。最后,对学习过程建模在学习管理系统中的应用提出了展望。     

A memetic grammar inference algorithm for language learning

An unsupervised incremental algorithm for grammar inference and its application to domain-specific language development are described. Grammatical inference is the process of learning a grammar from the set of positive and optionally negative sentences. Learning general context-free grammars is still considered a hard problem in machine learning and is not completely solved yet. The main contribution of the paper is a newly developed memetic algorithm, which is a population-based evolutionary algorithm enhanced with local search and a generalization process. The learning process is incremental since a new grammar is obtained from the current grammar and false negative samples, which are not parsed by the current grammar. Despite being incremental, the learning process is not sensitive to the order of samples. All important parts of this algorithm are explained and discussed. Finally, a case study of a domain specific language for rendering graphical objects is used to show the applicability of this approach.     

Learning,goals, and learning goals: A perspective on goal-driven learning

In cognitive science, artificial intelligence, psychology, and education, a growing body of research supports the view that the learning process is strongly influenced by the learner's goals. The fundamental tenet ofgoal-driven learning is that learning is largely an active and strategic process in which the learner, human or machine, attempts to identify and satisfy its information needs in the context of its tasks and goals, its prior knowledge, its capabilities, and environmental opportunities for learning. This article examines the motivations for adopting a goal-driven model of learning, the relationship between task goals and learning goals, the influences goals can have on learning, and the pragmatic implications of the goal-driven learning model. It presents a new integrative framework for understanding the goal-driven learning process and applies this framework to characterizing research on goal-driven learning.     

A process for post-implementation IT benchmarking

Post-implementation learning involves continuing improvements in how effectively information technology (IT) is utilized. This kind of IT learning is a core competency that may determine the competitiveness of firms in information intensive industries. While many chief information officers (CIOs) may have some experience with infrastructure, user satisfaction, or business process benchmarking, few firms benchmark how effectively IT is utilized or its impact on the user’s work.This paper proposes a web-enabled process for benchmarking IT outcomes (effective use and impacts) and diagnosing problems with the user’s learning. This process is based on an explicit causal model of how induced and autonomous learning factors drive IT usage and impacts. The proposed process enables internal versus “best-in-class” causal analysis. We discuss the common considerations and key issues involved in implementing this IT benchmarking process.     

一种基于多层感知器的机器人快速推理学习方法

从多层感知器原理分析出发,该文提出一种适变学习因子法用于对学习算法的改进,并将改进的算法用于“逃避”机器人推理网络的实例样本的学习。仿真结果表明,改进后BP的算法可显著加速网络训练速度,并且学习过程具有较好的收敛性及较强的鲁棒性.     

A flexible vision-based algorithm for a book sorting system

A flexible vision-based algorithm for a book sorting system is presented. The algorithm is based on a discrimination model that is adaptively generated for the current object classes by learning. The algorithm consists of an image normalization process, a feature element extraction process, a learning process, and a recognition process. The image normalization process extracts the contour of the object in an image, and geometrically normalizes the image. The feature extraction process converts the normalized image to the pyramidal representation, and the feature element is extracted from each resolution level. The learning process generates a discrimination model, which represents the differences between classes, based on hierarchical clustering. In the recognition process, the input images are hierarchically discriminated under the control of the decision tree. To evaluate the algorithm, a simulation system was implemented on a general-purpose computer and an image processor was developed     

A system design framework-driven implementation of a learning collaboratory

This paper describes a design process to support the development of a learning collaboratory, a distributed, computer-based, virtual space for learning and work. A learning collaboratory, as a distributed distance learning environment, offers great opportunities to expand the way people teach and learn and to broaden educational opportunities to an ever increasing range of learners. The challenge is to design distance learning technologies that engender meaningful learning experiences that take full advantage of the power of computer-mediated communication to support innovative learner-centered and collaborative interactions between students, teachers, subject experts, and resources. First, the paper describes the learning collaboratory design framework (LUCIDIFY), a design process that integrates methods and concepts from cognitive systems engineering, theories of learning and instruction, distributed computing, and computer-supported collaborative learning to guide the principled design of learning collaboratories. Next, the paper describes how LUCIDIFY was used in the design and implementation of the collaborative learning environment for operational systems (CLEOS), a learning collaboratory for teachers, students, and practitioners in the physical sciences. CLEOS features two virtual instrument tutorials, an asynchronous messaging system, a project-based design and management application, and a collaborative multi-user domain infrastructure.     

CMAC学习过程收敛性的研究

基于CMAC学习过程等价于求解线性方程组的(Gauss-Seidel迭代这一事实,研究 了学习过程的收敛性.利用矩阵分析方法,估计出了收敛的速度.考虑了作为节省存储空间措 施的hash编码的不利影响--破坏了收敛性态.从理论上分析了其存在的原因.     

一种基于角色跟踪的群体Agent再励学习算法

在多Agent系统中,通过学习可以使Agent不断增加和强化已有的知识与能力,并选择合理的动作最大化自己的利益．但目前有关Agent学习大都限于单Agent模式,或仅考虑Agent个体之间的对抗,没有考虑Agent的群体对抗,没有考虑Agent在团队中的角色,完全依赖对效用的感知来判断对手的策略,导致算法的收敛速度不高．因此,将单Agent学习推广到在非通信群体对抗环境下的群体Agent学习．考虑不同学习问题的特殊性,在学习模型中加入了角色属性,提出一种基于角色跟踪的群体Agent再励学习算法,并进行了实验分析．在学习过程中动态跟踪对手角色,并根据对手角色与其行为的匹配度动态决定学习速率,利用minmax-Q算法修正每个状态的效用值,最终加快学习的收敛速度,从而改进了Bowling和Littman等人的工作．