A Canonical Locally Named Representation of Binding

This paper is about completely formal representation of languages with binding. We have previously written about a representation following an approach going back to Frege, based on first-order syntax using distinct syntactic classes for locally bound variables vs. global or free variables?(Sato and Pollack, J Symb Comput 45:598?C616, 2010). The present paper differs from our previous work by being more abstract. Whereas we previously gave a particular concrete function for canonically choosing the names of binders, here we characterize abstractly the properties required of such a choice function to guarantee canonical representation, and focus on the metatheory of the representation, proving that it is in substitution preserving isomorphism with the nominal Isabelle representation of pure lambda terms. This metatheory is formalized in Isabelle/HOL. The final section outlines a formalization in Matita of a challenging language with multiple binding and simultaneous substitution. The Isabelle and Matita proof files are available online.     

基于特别的特征表示方法的局部线性KNN算法

提出了一种特别的特征表示方法,并在此基础上提出了一种基于特别的特征表示方法的局部线性K最近邻算法(locally linear K-nearest neighbor method,L~2KNN),并将之应用到人脸识别中。特别的特征表示方法是在传统的稀疏表示的基础上,加入了非负约束,改进了传统的稀疏表示的方法,在目标函数中增加了集群正则化项,然后优化新的目标函数得到一个新的近似的特征表示。L~2KNN算法具有最近邻集群效应(clustering effect of nearest neighbors,CENN),不仅可以增强测试样本与同类的训练样本之间的相关性,而且可以增强同类训练样本之间的相关性。L~2KNN算法进一步应用到L~2KNNc(L~2KNN-based classifier)分类器中,并提出一种系数截断的方法增加L~2KNNc分类器的泛化性能,进一步提高分类器的分类性能。在人脸数据集上的实验结果证明了上述结论。     

Multi-Level Shape Representation Using Global Deformations and Locally Adaptive Finite Elements

We present a model-based method for the multi-level shape, pose estimation and abstraction of an object's surface from range data. The surface shape is estimated based on the parameters of a superquadric that is subjected to global deformations (tapering and bending) and a varying number of levels of local deformations. Local deformations are implemented using locally adaptive finite elements whose shape functions are piecewise cubic functions with C ¹ continuity. The surface pose is estimated based on the model's translational and rotational degrees of freedom. The algorithm first does a coarse fit, solving for a first approximation to the translation, rotation and global deformation parameters and then does several passes of mesh refinement, by locally subdividing triangles based on the distance between the given datapoints and the model. The adaptive finite element algorithm ensures that during subdivision the desirable finite element mesh generation properties of conformity, non-degeneracy and smoothness are maintained. Each pass of the algorithm uses physics-based modeling techniques to iteratively adjust the global and local parameters of the model in response to forces that are computed from approximation errors between the model and the data. We present results demonstrating the multi-level shape representation for both sparse and dense range data.     

流形距离与压缩感知核稀疏投影的局部线性嵌入算法

流形学习算法的目的是发现嵌入在高维数据空间中的低维表示,现有的流形学习算法对邻域参数k和噪声比较敏感。针对此问题,文中提出一种流形距离与压缩感知核稀疏投影的局部线性嵌入算法,其核心思想是集成局部线性嵌入算法对高维流形结构数据的降维有效性与压缩感知核稀疏投影的强鉴别性,以实现高效有降噪流形学习。首先,在选择各样本点的近邻域时,采用流形距离代替欧氏距离度量数据间相似度的方法,创建能够正确反映流形内部结构的邻域图,解决以欧氏距离作为相似性度量时对邻域参数的敏感。其次,利用压缩感知核稀疏投影作为从高维观测空间到低维嵌入空间的映射,增强算法的鉴别性。最后,利用Matlab工具对实验数据集进行仿真,进一步验证所提算法的有效性。     

The Structure of Locally Orderless Images

We propose a representation of images in which a global, but not a local topology is defined. The topology is restricted to resolutions up to the extent of the local region of interest (ROI). Although the ROI's may contain many pixels, there is no spatial order on the pixels within the ROI, the only information preserved is the histogram of pixel values within the ROI's. This can be considered as an extreme case of a textel (texture element) image: The histogram is the limit of texture where the spatial order has been completely disregarded. We argue that locally orderless images are ubiquitous in perception and the visual arts. Formally, the orderless images are most aptly described by three mutually intertwined scale spaces. The scale parameters correspond to the pixellation (inner scale), the extent of the ROI's (outer scale) and the resolution in the histogram (tonal scale). We describe how to construct locally orderless images, how to render them, and how to use them in a variety of local and global image processing operations.     

The Representation of Fuzzy Knowledge

Abstract

A new AI programming language (called FUZZY) is introduced which provides a number of facilities for efficiently representing and manipulating fuzzy knowledge. A fuzzy associative net is maintained by the system, and procedures with associated “procedure demons” may be defined for the control of fuzzy processes. Such standard AI language features as a pattern-directed data access and procedure invocation mechanism and a backtrack control structure are also available.

This paper examines some general techniques for representing fuzzy knowledge in FUZZY, including the use of the associative net for the explicit representation of fuzzy sets and fuzzy relations, and the use of “deduce procedures” to implicitly define fuzzy sets, logical combinations of fuzzy sets, linguistic hedges, and fuzzy algorithms. The role of inference in a fuzzy environment is also discussed, and a technique for computing fuzzy inferences in FUZZY is examined.

The programming language FUZZY is implemented in LISP, and is currently running on a UNIVAC 1110 computer.     

The Computational Origin of Representation

Minds and Machines - Each of our theories of mental representation provides some insight into how the mind works. However, these insights often seem incompatible, as the debates between symbolic,...     

产品配置的知识表示

为按照用户的需要定制售卖产品的公司提供支持的基于知识的配置系统,产品配置器是人工智能技术的一个重要应用.本文首先描述了配置问题及其相关概念,然后分析了某些配置知识表示的优缺点,在此基础上提出了产品配置知识的图形表示方法,最后讨论了目前的一些热点研究问题.     

粗糙模糊集的近似表示

粗糙模糊集是利用粗糙集的 Pawlak 知识空间来近似刻画一个模糊集（不确定概念）的理论模型．粗糙模糊集用上、下近似模糊集作为目标概念的边界模糊集,它没有给出在当前知识基下如何得到目标模糊概念的近似模糊集或近似精确集的方法．文中首先给出模糊集的相似度（近似度）的概念,定义了 Pawlak 知识空间U／R 下的阶梯模糊集、均值模糊集、0．5-精确集等概念;然后分析得出U／R 知识空间下的均值模糊集是所有阶梯模糊集中与目标模糊集最接近的模糊集,U／R 知识空间下0．5-精确集是目标模糊集最接近的近似精确集;分析了均值模糊集、0．5-精确集分别与目标模糊集之间的相似度随知识粒度变化的变化规律．从新的视角提出了不确定性目标概念的近似表示和处理的方法,促进了不确定人工智能的发展．     

The Linguistic Subversion of Mental Representation

Embedded and embodied approaches to cognition urge that (1) complicated internal representations may be avoided by letting features of the environment drive behavior, and (2) environmental structures can play an enabling role in cognition, allowing prior cognitive processes to solve novel tasks. Such approaches are thus in a natural position to oppose the ??thesis of linguistic structuring??: The claim that the ability to use language results in a wholesale recapitulation of linguistic structure in onboard mental representation. Prominent examples of researchers adopting this critical stance include Andy Clark, Michael Wheeler, and Mark Rowlands. But is such opposition warranted? Since each of these authors advocate accounts of mental representation that are broadly connectionist, I survey research on formal language computation in artificial neural networks, and argue that results indicate a strong form of the linguistic structuring thesis is true: Internal representational systems recapitulate significant linguistic structure, even on a connectionist account of mental representation. I conclude by sketching how my conclusion can nonetheless be viewed as consistent with and complimentary to an embedded/embodied account of the role of linguistic structure in cognition.     

基于LOBA逻辑的言语行为表示

言语行为是多主体系统中一个有趣而重要的问题.该文从实际推理主体(practical reasoningagents)研究的角度对语用学中的言语行为进行了探讨.在多主体系统中言语行为的研究主要集中在3个方面:1)言语行为的本体描述;2)主体如何推理出合理的言语行为;3)主体如何正确处理其他主体发出的言语行为.这3个方面侧重点不同,但是相互间又紧密关联.重点讨论上述2)和3)两方面的内容,建立了一个主体认知过程的模型,并用可信主体逻辑LOBA(logic of believable agents)进行形式化表示.在主体认知过程的模型中,考虑包括主体的感知、信念、情绪、期望、目标、意图、承诺在内的各种认知成分,通过引入相应的认知动作来考虑这些认知成分之间的动态关系,并在此基础上描述主体如何产生和处理言语行为.在逻辑系统的构建上,LOBA逻辑扩展了KARO逻辑和LORA逻辑,将主体的情绪和认知动作都作为模态算子进行处理,并构建了3层语义模型以解释主体的认知动作.利用上述方法,LOBA可以在更细的粒度上来刻画主体的动态的实际推理过程.     

事件关系表示模型

事件关系的表示及事件推理是基于事件的知识处理的核心内容。文章提出了事件影响因子的概念来刻画事件间相互影响的强弱,给出了一种事件影响因子的计算方法。在此基础上,建立了事件关系图ERM(Event Relationship Map)来描述领域中事件之间的关系。依据事件关系和事件要素可以进行事件推理,重点阐述了ERM上基于关系的事件推理算法。最后,做了一个事件关系推理的实验,结果证明所提模型及算法与人的主观判断相一致,是合理可行的。     

The M-Space Feature Representation for SLAM

In this paper, a new feature representation for simultaneous localization and mapping (SLAM) is discussed. The representation addresses feature symmetries and constraints explicitly to make the basic model numerically robust. In previous SLAM work, complete initialization of features is typically performed prior to introduction of a new feature into the map. This results in delayed use of new data. To allow early use of sensory data, the new feature representation addresses the use of features that initially have been partially observed. This is achieved by explicitly modelling the subspace of a feature that has been observed. In addition to accounting for the special properties of each feature type, the commonalities can be exploited in the new representation to create a feature framework that allows for interchanging of SLAM algorithms, sensor and features. Experimental results are presented using a low-cost Web-cam, a laser range scanner, and combinations thereof.     

局部规则嵌入

引入了拓扑结构和规则拓扑结构的概念,为了寻求具有规则拓扑结构的低维数据集,构 造了拓扑结构规则性的度量,提出了保持数据集拓扑结构的局部规则嵌入方法。与LocallyLinear Embedding,LaplacianEigenmap等核特征映射方法相比,低维嵌入结果是近似规则的,与数据分类有 着更加自然的联系。最后的实例表明,与LLE和LaplacianEigenmap方法相比,该方法能更好地保持 数据集的类特性,揭示数据集的本征结构。     

Locally Injective Mappings

Mappings and deformations are ubiquitous in geometry processing, shape modeling, and animation. Numerous deformation energies have been proposed to tackle problems like mesh parameterization and volumetric deformations. We present an algorithm that modifies any deformation energy to guarantee a locally injective mapping, i.e., without inverted elements. Our formulation can be used to compute continuous planar or volumetric piecewise‐linear maps and it uses a barrier term to prevent inverted elements. Differently from previous methods, we carefully design both the barrier term and the associated numerical techniques to be able to provide immediate feedback to the user, enabling interactive manipulation of inversion‐free mappings. Stress tests show that our method robustly handles extreme deformations where previous techniques converge very slowly or even fail. We demonstrate that enforcing local injectivity increases fidelity of the results in applications such as shape deformation and parameterization.     

Locally Weighted Learning

This paper surveys locally weighted learning, a form of lazy learning and memory-based learning, and focuses on locally weighted linear regression. The survey discusses distance functions, smoothing parameters, weighting functions, local model structures, regularization of the estimates and bias, assessing predictions, handling noisy data and outliers, improving the quality of predictions by tuning fit parameters, interference between old and new data, implementing locally weighted learning efficiently, and applications of locally weighted learning. A companion paper surveys how locally weighted learning can be used in robot learning and control.     

The Representation of Numbers in Quantum Mechanics

Abstract. Earlier work on modular arithmetic of k-ary representations of length L of the natural numbers in quantum mechanics is extended here to k-ary representations of all natural numbers, and to integers and rational numbers. Since the length L is indeterminate, representations of states and operators using creation and annihilation operators for bosons and fermions are defined. Emphasis is on definitions and properties of operators corresponding to the basic operations whose properties are given by the axioms for each type of number. The importance of the requirement of efficient implementability for physical models of the axioms is emphasized. Based on this, successor operations for each value of j corresponding to +k ^j-1 are defined. It follows from the efficient implementability of these successors, which is the case for all computers, that implementation of the addition and multiplication operators, which are defined in terms of polynomially many iterations of the successors, should be efficient. This is not the case for definitions based on just the successor for j=1 . This is the only successor defined in the usual axioms of arithmetic.