PAC Learning of One-Dimensional Patterns

Developing the ability to recognize a landmark from a visual image of a robot's current location is a fundamental problem in robotics. We consider the problem of PAC-learning the concept class of geometric patterns where the target geometric pattern is a configuration ofk points on the real line. Each instance is a configuration ofn points on the real line, where it is labeled according to whether or not it visually resembles the target pattern. To capture the notion of visual resemblance we use the Hausdorff metric. Informally, two geometric patternsP andQ resemble each other under the Hausdorff metric if every point on one pattern is close to some point on the other pattern. We relate the concept class of geometric patterns to the landmark matching problem and then present a polynomial-time algorithm that PAC-learns the class of one-dimensional geometric patterns. We also present some experimental results on how our algorithm performs.     

Learning commutative deterministic finite state automata in polynomial time

We consider the problem of learning the commutative subclass of regular languages in the on-line model of predicting {0,1∼-valued functions from examples and reinforcements due to Littlestone [7,4]. We show that the entire class of commutative deterministic finite state automata (CDFAs) of an arbitrary alphabet sizek is predictable inO(s ^k) time with the worst case number of mistakes bounded above byO(s ^kk logs), wheres is the number of states in the target DFA. As a corollary, this result implies that the class of CDFAs is also PAC-learnable from random labeled examples in timeO(s ^k) with sample complexity, using a different class of representations. The mistake bound of our algorithm is within a polynomial, for a fixed alphabet size, of the lower boundO(s+k) we obtain by calculating the VC-dimension of the class. Our result also implies the predictability of the class of finite sets of commutative DFAs representing the finite unions of the languages accepted by the respective DFAs. Part of this work was supported by the Office of Naval Research under contract number N00014-87-K-0401 while the author was at the Department of Computer and Information Science, University of Pennsylvania, and N0014-86-K-0454 while at the Department of Computer and Information Sciences, U.C. Santa Cruz. The author’s email address is abe@IBL.CL.nec.co.jp     

PAC捕收剂选铜工艺研究

介绍新型PAC捕收剂用于某铜矿的选矿研究 ,采用优先浮选和混合浮选两个流程方案 ,均取得良好的结果 ,两种流程指标相近。铜精矿品位 2 2 %～ 2 3% ,铜回收率84%～ 85% ;硫精矿含硫 39%～ 40 % ,硫回收率 87%。     

基于PAC-Bayes边界理论的SVM模型选择方法

PAC-Bayes边界理论融合了贝叶斯定理和随机分类器的结构风险最小化原理,它作为一个理论框架,能有效评价机器学习算法的泛化性能。针对支持向量机（SVM）模型选择问题,通过分析PAC-Bayes边界理论框架及其在SVM上的应用,将PAC-Bayes边界理论与基于交叉验证的网格搜索法相结合,提出一种基于PAC-Bayes边界的SVM模型选择方法（PBB-GS）,实现快速优选SVM的惩罚系数和核函数参数。UCI数据集的实验结果表明该方法优选出的参数能使SVM具有较高的泛化性能,并具有简便快速、参数选择准确的优点,能有效改善SVM模型选择问题。     

结构化学习的噪声可学习性分析及其应用

噪声可学习性理论指出,有监督学习方法的性能会受到训练样本标记噪声的严重影响.然而,已有相关理论研究仅针对二类分类问题.致力于探究结构化学习问题受噪声影响的规律性.首先,注意到在结构化学习问题中,标注数据的噪声会在训练过程中被放大,使得训练过程中标记样本的噪声率高于标记样本的错误率.传统的噪声可学习性理论并未考虑结构化学习中的这一现象,从而低估了问题的复杂性.从结构化学习问题的噪声放大现象出发,提出了新的结构化学习问题的噪声可学习性理论.在此基础上,提出了有效训练数据规模的概念,这一指标可用于在实践中描述噪声学习问题的数据质量,并进一步分析了实际应用中的结构化学习模型在高噪声环境下向低阶模型回退的情况.实验结果证明了该理论的正确性及其在跨语言映射和协同训练方法中的应用价值和指导意义.     

基于罗克韦尔ControlLogix的玻壳成型冗余自控系统设计

本文介绍了基于美国罗克韦尔公司ControlLogix控制器的玻壳成型冗余自控系统,应用基于PROFIBUS—DP、MPI及Ethemet的网络通信手段,通过软冗余的方式实现对生产线设备的控制。作者阐述了该冗余控制系统的基本工作原理、软硬件构成与通信网络配置、功能特点及程序设计等方面的内容。     

Efficient PAC Learning for Episodic Tasks with Acyclic State Spaces

This paper considers the problem of computing an optimal policy for a Markov decision process, under lack of complete a priori knowledge of (1) the branching probability distributions determining the evolution of the process state upon the execution of the different actions, and (2) the probability distributions characterizing the immediate rewards returned by the environment as a result of the execution of these actions at different states of the process. In addition, it is assumed that the underlying process evolves in a repetitive, episodic manner, with each episode starting from a well-defined initial state and evolving over an acyclic state space. A novel efficient algorithm for this problem is proposed, and its convergence properties and computational complexity are rigorously characterized in the formal framework of computational learning theory. Furthermore, in the process of deriving the aforementioned results, the presented work generalizes Bechhofer’s “indifference-zone” approach for the ranking & selection problem, that arises in statistical inference theory, so that it applies to populations with bounded general distributions.

PAC学习模型研究

计算学习理论为比较两算法的性能提供了形式化的框架，并能确定某概念类的计算复杂度和样本复杂度。而PAC学习模型是计算学习理论的基础，它为研究学习及泛化问题提供了一种基本的概率框架：先介绍了基本的PVC学习模型并对其进行了深入的分析，给出了判断一概念类是否是PAC学习的方法；然后针对基本PAC学习模型的不足进行了相应的扩展；最后介绍了计算学习理论中的一些其它模型。     

基于分布式架构及PAC技术的风洞测试及控制系统设计

为准确分析飞行器气动载荷的实际变化规律,降低舱门、舱体类结构部件所受到的冲击载荷作用,设计基于分布式架构及PAC技术的风洞测试及控制系统。在Hadoop集群安装环境中,设置HBase加载模块,借助压电传感器结构与压力控制子回路,实现对加热器供气管路的指向性连接,完成风洞测试控制系统分布式架构集群的建立,解决飞行器舱门及舱体结构的气动载荷获取问题。以驱动性程序作为软件控制基础,将所有待处理的传感器信息及测试数据显示至相同控制界面中,实现对风洞测试控制信号的准确分析,完成基于PAC技术的风洞测试自适应控制研究。仿真实验表明,不断增大压电传感器所承受的气动载荷总量,在风洞测试控制系统的支持下,舱门、舱体所受的实际冲击载荷作用均下降至4000GB左右,能够满足缓解飞行器气动载荷压力的测试初衷。     

污水处理中物化与兼性生化低温下的协同作用

针对兼性生化低温状态去除效果差、污泥易流失等问题,提出采取物化兼性生化联用法来提高其处理效果.并采用对比法研究物化、兼性生化及二者联用技术处理低温城市污水.研究结果表明在聚合氯化铝（PAC）投加量为20mg/L时,物化与兼性生化在COD、浊度及TP的去除方面表现出良好的协同作用,但脱氮效果一般;二者协同作用能以较小的投药量有效改善低温状态兼性生化处理效果及污泥流失现象,为后续生态单元的稳定运行提供了保障.