From Term Models to Domains

Let B be the closed term model of the λ-calculus in which terms with the same Böhm tree are identified. We investigate which partial equivalence relations (PERs) on B can be regarded as predomains or domains. Inside the realizability topos on B, such PERs can be regarded simply as sets in a particular model of constructive set theory. No well-behaved partial order has been identified for any class of PERs; but it is still possible to isolate those PERs which have "suprema of chains" in a certain sense, and all maps between such PERs in the model preserve such suprema of chains. One can also define what it means for such a PER to have a "bottom"; partial function spaces provide an example. For these PERs, fixed points of arbitrary endofunctions exist and are computed by the fixed point combinator y. The categories of predomains are closed under the formation of total and partial function spaces, polymorphic types, and convex powerdomains. They in fact form reflective subcategories of the realizability topos; and in this set-theoretic context, these constructions are very simple to describe. We illustrate the theory by discussing an interpretation of PCF, and proving a computational adequacy theorem. None of the usual counterexamples to full abstraction are applicable to our model.     

From UML Models to Graph Transformation Systems

In this paper we present an approach that allows to validate properties of UML models. The approach is based on an integrated semantics for central parts of the UML. We formally cover UML use case, class, object, statechart, collaboration, and sequence diagrams. Additionally full OCL is supported in the common UML fashion. Our semantics is based on the translation of a UML model into a graph transformation system consisting of graph transformation rules and a working graph that represents the system state. By applying the rules on the working graph, the evolution of the modeled system is simulated.     

From Images to Shape Models for Object Detection

We present an object class detection approach which fully integrates the complementary strengths offered by shape matchers. Like an object detector, it can learn class models directly from images, and can localize novel instances in the presence of intra-class variations, clutter, and scale changes. Like a shape matcher, it finds the boundaries of objects, rather than just their bounding-boxes. This is achieved by a novel technique for learning a shape model of an object class given images of example instances. Furthermore, we also integrate Hough-style voting with a non-rigid point matching algorithm to localize the model in cluttered images. As demonstrated by an extensive evaluation, our method can localize object boundaries accurately and does not need segmented examples for training (only bounding-boxes).     

Learning to Parse Natural Language with Maximum Entropy Models

This paper presents a machine learning system for parsing natural language that learns from manually parsed example sentences, and parses unseen data at state-of-the-art accuracies. Its machine learning technology, based on the maximum entropy framework, is highly reusable and not specific to the parsing problem, while the linguistic hints that it uses to learn can be specified concisely. It therefore requires a minimal amount of human effort and linguistic knowledge for its construction. In practice, the running time of the parser on a test sentence is linear with respect to the sentence length. We also demonstrate that the parser can train from other domains without modification to the modeling framework or the linguistic hints it uses to learn. Furthermore, this paper shows that research into rescoring the top 20 parses returned by the parser might yield accuracies dramatically higher than the state-of-the-art.     

探析自然形态对室内设计的启示

设计艺术的历史和实践向我们表明,自然是设计永恒的表现主题之一,也是设计活动取之不竭的素材资源。设计源于自然而又高于自然,自然界是设计的源泉和动力。本文主要是分析自然、自然形态和室内设计的关系,从中得出自然形态对室内设计的几点启示。     

隐马尔可夫模型及其在自然语言处理中的应用

基于隐马尔可夫模型(HMM)对汉语文本进行了词性标注,首先介绍隐马尔可夫模型的基本概念,然后着重介绍了隐马尔可夫模型的三个基本问题以及解决问题的基本算法,最后演示了隐马尔可夫模型在词性标注中的简单应用.     

模拟自然形态的儿童包装设计

面对儿童包装市场呈现千篇一律使用卡通形象这一现象,本文提出运用模拟自然形态这一新的设计手法在儿童包装设计的外部造型以及内部结构封面。     

Natural Architecture and Constructed Forms: Structure and Surfaces from Idea to Drawing

This work grew out of didactic experience in architecture classes at the universities of Florence and Parma. The comprehension of geometric schemes in regular organic objects formed the basis of teaching drawing and scientific representation, such as formal architectural synthesis. This exercise may offer also a valid starting point to help students approach mathematics, and help them to imagine and plan the increasingly complex surfaces of late contemporary architecture.     

自然语言处理中的模型

本文简单介绍了自然语言处理发展的现状,讨论了自然语言处理模型,将其分为三大类：分析模型、统计模型及混合模型。具体介绍了分析模型原理及存在的问题,重点讨论了各种统计模型的特点及局限性,最后简单介绍了混合模型,并指出目前自然语言处理技术中存在的问题。     

Anisotropic Smoothness Classes: From Finite Element Approximation to Image Models

We propose and study quantitative measures of smoothness f ? A(f) which are adapted to anisotropic features such as edges in images or shocks in PDE’s. These quantities govern the rate of approximation by adaptive finite elements, when no constraint is imposed on the aspect ratio of the triangles, the simplest example being \(A_{p}(f)=\|\sqrt{|\mathrm{det}(d^{2}f)|}\|_{L^{\tau}}\) which appears when approximating in the L ^p norm by piecewise linear elements when \(\frac{1}{\tau}=\frac{1}{p}+1\). The quantities A(f) are not semi-norms, and therefore cannot be used to define linear function spaces. We show that these quantities can be well defined by mollification when f has jump discontinuities along piecewise smooth curves. This motivates for using them in image processing as an alternative to the frequently used total variation semi-norm which does not account for the smoothness of the edges.     

Significance of Models of Computation,from Turing Model to Natural Computation

The increased interactivity and connectivity of computational devices along with the spreading of computational tools and computational thinking across the fields, has changed our understanding of the nature of computing. In the course of this development computing models have been extended from the initial abstract symbol manipulating mechanisms of stand-alone, discrete sequential machines, to the models of natural computing in the physical world, generally concurrent asynchronous processes capable of modelling living systems, their informational structures and dynamics on both symbolic and sub-symbolic information processing levels. Present account of models of computation highlights several topics of importance for the development of new understanding of computing and its role: natural computation and the relationship between the model and physical implementation, interactivity as fundamental for computational modelling of concurrent information processing systems such as living organisms and their networks, and the new developments in logic needed to support this generalized framework. Computing understood as information processing is closely related to natural sciences; it helps us recognize connections between sciences, and provides a unified approach for modeling and simulating of both living and non-living systems.     

自然语言处理的计算模型

本文讨论自然语言处理的计算模型。目前已经存在有各种类型的语言计算模型,如分析模型、概率统计模型、混合模型等,这些模型各具特色,并存在其自身的局限性。自然语言处理作为一个不适定问题,我们将讨论求解这类问题的本质困难,面临的挑战,以及解决这些困难的途径。     

自然图像中混叠的概率模型

我们为建立自然图像中混叠的概率模型提供了一个数学框架。假设：(1)图像是由三维物体的二维投影轮廓组成．(2)在简化条件下．我们推导出自然图像的一种解析概率密度函数。已经证明．这种解析表达式可以很好地比配观测到的密度函数(直方图)。我们首先推导图像像素的边缘概率密度函数，然后推广到多维边缘概率密度函数，最后提出了几种改进措施。     

Management Information Models Integration: From Existing Approaches to New Unifying Guidelines

The evolution towards a higher-level managementrequires management information obtained from physicalto application elements as well as distinct resources(e.g., PC, UNIX workstations). This issue is difficult because the modeling of managementinformation is realized in many different ways and theinformation model integration represents an acutecurrent concern. In this paper we discuss thisintegration issue by specifying the sources of ManagementInformation Base (MIB) heterogeneity and identifyingtheoretical means characterizing approaches dealing withinformation models integration. Based on these results, the analysis of some existingintegration approaches led to dissatisfactions thusjustifying our contribution: integration guidelines andtheir implementation.     

Parallel Factories for Smart Industrial Operations: From Big AI Models to Field Foundational Models and Scenarios Engineering

The rapid advancement of fundamental theories and computing capacity has brought artificial intelligence, internet of things, extended reality, and many other new intelligent technologies into our daily lives. Due to the lack of interpretability and reliability guarantees, it is extremely challenging to apply these technologies directly to real-world industrial systems. Here we present a new paradigm for establishing parallel factories in metaverses to accelerate the deployment of intelligent technologies in real-world industrial systems: QAII-1.0. Based on cyber-physical-social systems, QAII-1.0 incorporates complex social and human factors into the design and analysis of industrial operations and is capable of handling industrial operations involving complex social and human behaviors. In QAII-1.0, a field foundational model called EuArtisan combined with scenarios engineering is developed to improve the intelligence of industrial systems while ensuring industrial interpretability and reliability. Finally, parallel oil fields in metaverses are established to demonstrate the operating procedure of QAII-1.0.      

Dynamic Spatial Equilibrium Models: an Application to the Natural Gas Spot Markets

Networks and Spatial Economics - European gas markets have gone through profound restructuring processes in the last 20 years. Directive 98/30/EC represented the first attempt to liberalize this...     

Mining Appearance Models Directly From Compressed Video

In this paper, we propose an approach for learning appearance models of moving objects directly from compressed video. The appearance of a moving object changes dynamically in video due to varying object poses, lighting conditions, and partial occlusions. Efficiently mining the appearance models of objects is a crucial and challenging technology to support content-based video coding, clustering, indexing, and retrieval at the object level. The proposed approach learns the appearance models of moving objects in the spatial-temporal dimension of video data by taking advantage of the MPEG video compression format. It detects a moving object and recovers the trajectory of each macroblock covered by the object using the motion vector present in the compressed stream. The appearances are then reconstructed in the DCT domain along the object's trajectory, and modeled as a mixture of Gaussians (MoG) using DCT coefficients. We prove that, under certain assumptions, the MoG model learned from the DCT domain can achieve pixel-level accuracy when transformed back to the spatial domain, and has a better band-selectivity compared to the MoG model learned in the spatial domain. We finally cluster the MoG models to merge the appearance models of the same object together for object-level content analysis.     

自然语言处理预训练模型的研究综述

近年来,深度学习技术被广泛应用于各个领域,基于深度学习的预处理模型将自然语言处理带入一个新时代。预训练模型的目标是如何使预训练好的模型处于良好的初始状态,在下游任务中达到更好的性能表现。对预训练技术及其发展历史进行介绍,并按照模型特点划分为基于概率统计的传统模型和基于深度学习的新式模型进行综述;简要分析传统预训练模型的特点及局限性,重点介绍基于深度学习的预训练模型,并针对它们在下游任务的表现进行对比评估;梳理出具有启发意义的新式预训练模型,简述这些模型的改进机制以及在下游任务中取得的性能提升;总结目前预训练的模型所面临的问题,并对后续发展趋势进行展望。