核函数对v-支持向量机的泛化能力影响分析

支持向量机在模式分类中得到了很好的应用。对于线性不可分的样本空间,需要寻找核函数,将线性不可分的样本集映射到另一个高维线性空间。支持向量机的泛化能力直接影响其实际应用效果。本文讨论了v-支持向量机的泛化能力的一个估计,定性分析了核函数对v-支持向量机的泛化能力的影响,并就高斯核函数对v-支持向量机的泛化能力的
的影响进行了具体分析。     

Self-learning energy management for plug-in hybrid electric bus considering expert experience and generalization performance

A self-learning energy management is proposed for plug-in hybrid electric bus, by combining Q-Learning (QL) and Pontryagin's minimum principle algorithms. Different from the existing strategies, the expert experience and generalization performance are focused in the proposed strategy. The expert experience is designed as the approximately optimal reference state-of-charge (SOC) trajectories, and the generalization performance is enhanced by a multiply driving cycle training method. In specific, an efficient zone of SOC is firstly designed based on the approximately optimal reference SOC trajectories. Then, the agent of the QL is trained off-line by taking the expert experience as reference SOC trajectories. Finally, an adaptive strategy is proposed based on the well-trained agent. Specially, two different reward functions are defined. That is, the reward function in the off-line training mainly considers the tracking performance between the expert experience and the SOC, while mainly considering the punishment in the adaptive strategy. Simulation results show that the proposed strategy has good generalization performance and can improve the fuel economy by 22.49%, compared to a charge depleting-charge sustaining (CDCS) strategy.     

Generalizing linguistic structures under high attention demands.

We explored whether the generalization of rules based on simple structures depends on attention. Participants were exposed to a stream of artificial words that followed a simple syllabic structure (ABA or AAB), overlaid on a sequence of familiar noises. After passively listening, participants successfully recognized the individual words present in the stream among foils, and they were able to generalize the underlying word structure to new exemplars. Yet, when attention was diverted from the speech stream (by requiring participants to monitor the sequence of noises), recognition of the individual words fell dramatically irrespective of word structure, whereas generalization depended on stimulus structure. For structures based on vowel repetitions across nonadjacent syllables (ABA; Experiment 1), generalization was affected by attention. In contrast, for structures based on adjacent repetitions (AAB; Experiment 2), generalization capacity was unaffected by attention. This pattern of results was replicated under favorable conditions for generalization, such as increased token variability and the implementation of the rule over whole syllables (Experiments 3 and 4). These results suggest a differential effect of attention on rule learning and generalization depending on stimulus structure. (PsycINFO Database Record (c) 2011 APA, all rights reserved)     

基于粗集理论的一种数据泛化方法

传统的粗集理论只能对数据库中的离散属性进行处理,所以对存在连续属性的数据库必须进行离散化处理。经过初次离散化后的信息系统往往包含的等价类数过多。文中提出了一种数据泛化方法,利用决策表相容性的反馈信息对经过初次离散化的信息系统进行处理。结果表明,该方法能够有效地提高规则的统计意义及解释能力,推导出来的规则对待识样本具有更好的适应性。     

船舶大功率发电机混沌神经网络建模

在分析和研究了Aihara神经元混沌特性的基础上,建立了基于Aihara混沌神经元的Elman局部递归混沌神经网络（CNN）,神经元引入混沌特性后增强了神经网络对非线性映射的全局逼近能力.在船舶大功率同步发电机建模中,以船用柴油机输出转矩功率和发电机输入励磁电流作为CNN建模与辨识的输入参数;以发电机的输出频率、发电机端电压和输出电流作为CNN建模与辨识的输出参数;采用有导师学习方式,运用基于BP的动态训练方法,最终完成了船舶大功率发电机的动态建模.与其它的ANN建模相比较,用CNN建立的模型的隐层神经元数量少,系统的泛化能力强.     

一种基于母线层的地图综合方法

针对目前地图综合中存在的一些问题，提出了一种基于母线层净数据的地图综合方法。     

Poitín: Distilling Theorems From Conjectures

In this paper, we describe a new fully automatic theorem prover called Poitín which makes use of a novel transformation algorithm called distillation to prove input conjectures. The input conjectures are defined in a functional language and are transformed using the distillation algorithm. The result of this transformation can be easily inspected to see whether the original conjecture is true. Possible divergence of the transformation algorithm is detected, and this information is used to perform generalizations to ensure termination. We give several examples of the application of the theorem prover, and compare it to related work.     

神经网络集成

神经网络集成通过训练多个神经网络并将成结论进行合成，可以显著地提高学习系统的泛化能力。它不仅有助于科学家对机器学习和神经的深入研究，还有助于普通工程技术人员利用神经网络技术来解决真实世界中的问题。因此，它被视为一种广阔应用前景的工程化神经计算技术，已经成为机器学习和神经计算领域的研究热点。该文从实现方法、理论分析和应用成果等三个方面综述了神经网络集成的国际研究现状，并对该领域值得进一步研究的一些问题进行了讨论。     

广义序偶的优化方法

本文在文献［１］的基础上引入了松驰量的概念，解决了在ＣＰＭ网络图中，在Ｎ＞２个平行工序中，预先指定一个工序的前提下，在剩下的Ｎ－１个工序中，选择一个工序与指定工序形成一个序偶的最优化问题，并举例说明了它的应用及该方法的优点。     

An Efficient Method To Estimate Bagging's Generalization Error

Bagging (Breiman, 1994a) is a technique that tries to improve a learning algorithm's performance by using bootstrap replicates of the training set (Efron & Tibshirani, 1993, Efron, 1979). The computational requirements for estimating the resultant generalization error on a test set by means of cross-validation are often prohibitive, for leave-one-out cross-validation one needs to train the underlying algorithm on the order of m times, where m is the size of the training set and is the number of replicates. This paper presents several techniques for estimating the generalization error of a bagged learning algorithm without invoking yet more training of the underlying learning algorithm (beyond that of the bagging itself), as is required by cross-validation-based estimation. These techniques all exploit the bias-variance decomposition (Geman, Bienenstock & Doursat, 1992, Wolpert, 1996). The best of our estimators also exploits stacking (Wolpert, 1992). In a set of experiments reported here, it was found to be more accurate than both the alternative cross-validation-based estimator of the bagged algorithm's error and the cross-validation-based estimator of the underlying algorithm's error. This improvement was particularly pronounced for small test sets. This suggests a novel justification for using bagging—more accurate estimation of the generalization error than is possible without bagging.