基于进化规划的神经网络群的设计方法

提出一种基于进化规划的神经网络群的自动设计方法．该方法不仅使得神经网络群中的个体网络倾向于完成不同的子任务，同时各神经网络个体在进化过程中不断寻找最好的协作关系，而且神经网络群的规模和结构不需预先设定．仿真试验表明，该算法是有效的。     

求解部分可观测马氏决策过程的强化学习算法

针对部分可观测马氏决策过程(POMDP)中，由于感知混淆现象的存在，利用Sarsa等算法得到的无记忆策略可能发生振荡的现象，研究了一种基于记忆的强化学习算法——CPnSarsa(λ)学习算法来解决该问题．它通过重新定义状态，Agent结合观测历史来识别混淆状态．将CPnSarsa(λ)算法应用到一些典型的POMDP，最后得到的是最优或近似最优策略，与以往算法相比，该算法的收敛速度有了很大提高．     

采样算子调整的径向基网络增量映射学习算法

为了提高增量映射学习(IPL)算法的效率,调整了径向基神经网络基函数的中心及方差,以达到调整采样算子的目的,同时,通过神经元函数相关性的计算,确定添加新神经元时,相关函数的阈值,为系统结构调整提供相应依据.新方法步骤相对简单,所以算法速度较快;仿真结果表明,由于系统参数得到调整,对于同一问题,改进IPL算法得到的径向基神经网络结构较一般算法得到的网络结构简单,输出结果也较为精确.     

多示例学习及其研究现状

较全面地介绍和分析了第4种机器学习框架的多示例学习(MIL)．首先通过数学表达式对多示例学习进行描述，概括了其主要性质；然后总结了目前主要的求解多示例学习问题的算法，剖析了这些算法的主要思想；最后对多示例学习的未来发展作了展望．     

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.     

基于内分泌调节机制的机器人行为规划算法及其应用研究

借鉴内分泌系统对神经系统与遗传系统的高层调节机制，提出了一种新的基于内分泌调节机制的机器人行为规划算法．此算法中机器人通过神经系统接受环境信息并进行行为决策，行为决策的效果通过一种情感学习模型进行反馈．情感学习模型根据机器人的内、外环境状态,产生情感因子(即生物激素)，再由情感因子来调节神经系统的记忆和行为决策，最后神经系统的记忆与行为模式又由遗传系统得以继承．该算法有效避免了神经系统复杂的自学习过程。同时也保证机器人有较强的自适应能力．为了验证算法的有效性，本文做了机器人足球队守门员训练的仿真实验，结果也表明该算法具有很强的自适应学习能力．     

基于BP神经网络的网上学习评价方法

利用BP神经网络并结合聚类分析技术,提出了一个面向网上学习评价的新型评价方法:在需要评价的大量数据中使用聚类分析技术选择部分对象的数据,让老师去评价打分,然后将这些结果作为BP神经网络的训练样本,让网络学会老师的评价方法,然后再将网络应用到其他对象的数据,进行网上学习评价仿真。文中给出了一个网上学习评价方法模型和相应实例,该方法在网上学习分班管理中,对学生学习能力进行评价时,得到了满意的结果。     

Learning Perceptrons and Piecewise Linear Classifiers Sensitive to Example Dependent Costs

This article considers the cost dependent construction of linear and piecewise linear classifiers. Classical learning algorithms from the fields of artificial neural networks and machine learning consider either no costs at all or allow only costs that depend on the classes of the examples that are used for learning. In contrast to class dependent costs, we consider costs that are example, i.e. feature and class dependent. We present a cost sensitive extension of a modified version of the well-known perceptron algorithm that can also be applied in cases, where the classes are linearly non-separable. We also present an extended version of the hybrid learning algorithm DIPOL, that can be applied in the case of linear non-separability, multi-modal class distributions, and multi-class learning problems. We show that the consideration of example dependent costs is a true extension of class dependent costs. The approach is general and can be extended to other neural network architectures like multi-layer perceptrons and radial basis function networks.     

Instance-Based Regression by Partitioning Feature Projections

A new instance-based learning method is presented for regression problems with high-dimensional data. As an instance-based approach, the conventional method, KNN, is very popular for classification. Although KNN performs well on classification tasks, it does not perform as well on regression problems. We have developed a new instance-based method, called Regression by Partitioning Feature Projections (RPFP) which is designed to meet the requirement for a lazy method that achieves high levels of accuracy on regression problems. RPFP gives better performance than well-known eager approaches found in machine learning and statistics such as MARS, rule-based regression, and regression tree induction systems. The most important property of RPFP is that it is a projection-based approach that can handle interactions. We show that it outperforms existing eager or lazy approaches on many domains when there are many missing values in the training data.     

Concept mapping your Web searches: a design rationale and Web-enabled application

Although it has become very common to use World Wide Web‐based information in many educational settings, there has been little research on how to better search and organize Web‐based information. This paper discusses the shortcomings of Web search engines and Web browsers as learning environments and describes an alternative Web search environment that combines a concept mapping and a data mining technique to address their drawbacks.