以分形维数测算建筑几何图形的视觉复杂度

在以往对建筑创作的解析中常以"丰富的细节"、"与自然相和谐"等词汇来描述设计,针对这种感性有余但缺乏清晰量化标准的现象,提出以分形维数作为量化建筑设计几何构成的方法.结合计算机编程辅助,将维数计算中的盒维数法与人对建筑的视觉观察距离相联系,提出"视觉复杂度"与"分形维数走势图"的概念,使之更适用于建筑学领域,并以此为基础,首先对人们所熟知的建筑师生平建筑作品进行维数计算,确定分析方法的可靠性,再进一步讨论维数计算在空间路径视觉体验以及设计初期在建筑周围建立视觉场这2个方面的应用.计算结果表明,维数信息可以作为一种明确的量化方法来探索隐藏在建筑外观背后的数字特征.     

普适计算模式下的人机交互

普适计算使得信息空间与人们生活的物理空间相融合,与此相应人机接口也将随之扩展到人们生活工作的整个三维物理空间.因此需要研究物理空间中的人机交互方式.在传统的计算模式下,交互环境的物理因素不影响人机交互.而在普适计算的模式下,用户和环境的物理因素将成为交互的重要因素,这将使人机交互的性质产生一系列的变化,其中包括:人机交互本质上是与信息空间的交互;交互接口扩展到日常生活的用品和环境;动态的人机交互上下文;蕴含人机交互.     

计算语用学研究的途径和方法

计算语用学是一门新兴的计算语言学分支,主要从计算的角度研究语言理解与语境之间的关系。哲学和语言学角度的语用学研究成果为计算语用学的发展打下了基础,而形式语用学的发展又为建立科学的计算模型提供了可行的参考。文章在已有研究成果的基础上,结合语言学领域语用学研究的主要论题和形式语用学研究的主要方法与手段,探讨了计算语用学研究的实现途径和方法,提出了计算语用学研究所做的主要工作,包括语言理解与推理的关系、溯因推理及其在自然语言处理中的应用、信任推理、动态语境的构建等。这项工作为计算语用学的应用研究提供了一种崭新的思路。     

R2空间上分布数据的多重分形维数谱计算和分形特征提取

近年来多重分形的概念在物理、化学等领域得到了发展和应用 ,在这些领域中 ,这种方法显示出了对于研究物理和化学量的空间分布是很有用的 .多重分形谱的计算是其中重要而又较难处理的问题 .从多重分形的理论出发 ,讨论了在数据处理的实际工作中有广泛应用的二维空间中多重分形谱的计算及分形特征提取的算法 ,介绍了算法的数学原理 ,描述了完整的算法流程 ,并给出了此算法的一个计算实例     

基于普适计算的学习框架的研究

普适计算(Pervasive/Ubiquitous Computing)是继主机计算、桌面计算之后发展起来的一种新的计算模式,但它在教育和学习领域还涉足甚微.随着技术的不断进步和学习科学理论的发展,普适计算与教学环境相结合是不可抵挡的趋势.普适学习环境就是将普适计算应用到人类的学习环境中,使其实现无处不在的学习这一特点.文章在总结普适计算及普适学习环境相关概念的基础上,通过研究分析-个比较成熟的普适学习环境的个案,提出了实现这一环境的框架模型及相关技术.     

社会感知计算:概念、问题及其研究进展

普适计算技术的发展极大地丰富和增强了人类获取数据的途径和能力,如何利用这些感知数据,理解人类的社会行为与活动,实现计算“以人为中心”并为社会服务的目标,是当前信息领域的重要问题.本文介绍了计算机科学领域的一个刚刚兴起的研究主题——社会感知计算.社会感知计算旨在通过人类生活空间日益部署的大规模多种类传感设备,实时感知识别社会个体的行为,分析挖掘群体社会交互特征和规律,辅助个体社会行为,支持社群的互动、沟通和协作.论文讨论了社会感知计算的概念、起源、模型和主要研究问题,综述了社会感知计算典型系统与应用、数据感知、行为与交互分析、社会理论与规律验证以及社会交互高效支持等方面的研究进展.     

面向图像识别的卷积神经网络鲁棒性研究进展

卷积神经网络是目前人工智能领域在图像识别与处理相关应用中的关键技术之一,广泛的应用使对其鲁棒性研究的重要性不断凸显。以往对于卷积神经网络鲁棒性的研究较为笼统,且多集中在对抗鲁棒性方面。这难以更深入地研究神经网络鲁棒性的发生机制,已经不适应人工智能的发展。引入神经科学的相关研究,提出了视觉鲁棒性的概念,通过研究神经网络模型与人类视觉系统的相似性,揭示了神经网络鲁棒性的内在缺陷。回顾了近年来神经网络鲁棒性的研究现状,并分析了神经网络模型缺乏鲁棒性的原因。神经网络缺乏鲁棒性体现在其对于微小扰动的敏感性,其原因在于神经网络会更倾向于学习人类难以感知的高频信息用于计算和推理。而这部分高频信息很容易被扰动所破坏,最终导致模型出现判断错误。传统鲁棒性的研究大多关注模型的数学性质,无法突破神经网络的天然局限性。视觉鲁棒性在传统鲁棒性的概念上进行拓展。传统鲁棒性概念衡量模型对于失真变形的图像样本的辨识能力,失真样本与原始干净样本在鲁棒模型上都能保持正确的输出。视觉鲁棒性衡量模型与人类判别能力的一致性。这需要将神经科学和心理学的研究方法、成果与人工智能相结合。回顾了神经科学在视觉领域的发展,讨论了认知心理学的研究方法在神经网络鲁棒性研究上的应用。人类视觉系统在学习和抽象能力上具有优势,神经网络模型在计算和记忆速度方面强于人类。人脑的生理结构与神经网络模型的逻辑结构的差异是导致神经网络鲁棒性问题的关键因素。视觉鲁棒性的研究需要对人类的视觉系统有更深刻的理解。揭示人类视觉系统与神经网络模型在认知机制上的差异,并对算法进行有效的改进,这是神经网络鲁棒性乃至人工智能算法的主要发展趋势。     

完美球本质--论分布系统软件开发技术

软件开发实践中存在的隐合成分和无法回避的"不够完美",就是现实软件开发项目中的无法控制或未知部分,这违反现存的大部分软件开发方法的基础,如一致性.完美球却是基于二重性,把微观世界的一些成分和复杂系统相映射.这是探索先进的西方科学技术和古代东方哲学的产物.分析由"陈述","思想"和"客观事实"组成的三角形,以说明完美点相区别的三角形.分布系统的测不准关系阐明:代码(代表可用产品)和目标(代表软件产品的性能)不能同时确定.在解释软件系统与人体间的联系中表明在气功哲学概念和软件开发概念之间可建立的某种映射关系.在完美球范畴下的软件开发强调生动活跃的学习行为,而不仅看重的自动机行为.用完美球替代特定目标点或动态可修改的目标点.系统复杂性日益增加,逐步减少概率论和预定计划影响.列举完美球少许应用.     

基于领域本体的语义相似度计算研究

本文介绍了有关本体的知识以及在领域本体参照下三种语义相似度的计算模型,并针对这三种计算模型的优缺点和领域本体所特有的性质提出了一种改进的基于领域本体的语义相似度计算模型.该计算模型的基本思想是：以基于距离的计算模型为基础,把概念的信息内容和概念的属性作为两个决策因子.实验结果表明,该方法能够比较准确地反映概
念之间的语义关系,为概念之间的语义关系提供一种有效的量化.     

基于本体和相似图的概念语义相似度计算

概念语义相似度计算的研究是人工智能最基础和最重要的课题之一,借鉴现有的概念建模思想和工具,提出一种综合的计算形式概念分析中概念间语义相似度的算法.通过分析传统的计算方法,对存在的问题进行改进,结合领域本体和FCA的思想,通过相似图和候选属性对集合等定义计算FCA中概念间的语义相似度.应用实例的结果表明计算结果与人类的主观判断基本一致.文中的方法对概念间语义相似度计算是可行的,使用该方法可以获取在语义上和用户请求最接近的结果.     

Philosophy of Mind Is (in Part) Philosophy of Computer Science

In this paper I argue that whether or not a computer can be built that passes the Turing test is a central question in the philosophy of mind. Then I show that the possibility of building such a computer depends on open questions in the philosophy of computer science: the physical Church-Turing thesis and the extended Church-Turing thesis. I use the link between the issues identified in philosophy of mind and philosophy of computer science to respond to a prominent argument against the possibility of building a machine that passes the Turing test. Finally, I respond to objections against the proposed link between questions in the philosophy of mind and philosophy of computer science.     

The New Mind: thinking beyond the head

Throughout much of the modern period, the human mind has been regarded as a property of the brain and therefore something confined to the inside of the head—a view commonly known as ‘internalism’. But recent works in cognitive science, philosophy, and anthropology, as well as certain trends in the development of technology, suggest an emerging view of the mind as a process not confined to the brain but spread through the body and world—an outlook covered by a family of views labelled ‘externalism’. In this paper, we will suggest there is now sufficient momentum in favour of externalism of various kinds to mark a historical shift in the way the mind is understood. We dub this emerging externalist tendency the ‘New Mind’. Key properties of the New Mind will be summarised and some of its implications considered in areas such as art and culture, technology, and the science of consciousness.     

Transcending the meat: immersive technologies and computer mediated bodies

In this paper we will call into question the philosophical grounding for the belief that our mind can in principle be removed from, or transcend, our bodies. We will show that modern immersive technology, such as virtual and web technologies, tacitly attempt to implement this philosophy. We will find that there is a growing community called the Transhumanists who are a loosely knit group of highly educated hi-tech professionals and scientists who explicitly accept the transcendent mind hypothesis. Through the work and influence of these professionals values that are antagonistic to the body enter, explicitly or tacitly, into computer technology. It is our claim that the transcendent mind hypothesis is in error and that immersive technologies have to take seriously issues regarding the embodied nature of their users and that this embodiment can not be transcended in any meaningful way.     

Turing Test: 50 Years Later

The Turing Test is one of the most disputed topics in artificial intelligence, philosophy of mind, and cognitive science. This paper is a review of the past 50 years of the Turing Test. Philosophical debates, practical developments and repercussions in related disciplines are all covered. We discuss Turing's ideas in detail and present the important comments that have been made on them. Within this context, behaviorism, consciousness, the `other minds' problem, and similar topics in philosophy of mind are discussed. We also cover the sociological and psychological aspects of the Turing Test. Finally, we look at the current situation and analyze programs that have been developed with the aim of passing the Turing Test. We conclude that the Turing Test has been, and will continue to be, an influential and controversial topic.     

试探形式美的生成机制

本文主要探讨形式美的根源问题,即什么原因造成了人类在形式上的共同审美偏好。通过对人的基本生理特征和心理特征分析,尝试给出了形式美规律产生的两个主要原因,分别是人类生理上的舒适性要求和人类心理上的求变性要求。     

Towards a linear general type-2 fuzzy logic based approach for computing with words

Within the last two decades, the paradigm of Computing With Words (CWW) has been gaining more attention. Mainly, CWW has an exciting vision which tries to tackle the problem of human intelligence by taking the human mind as a role model. The human intelligence has been investigated by various disciplines including psychology, philosophy, neuroscience, linguistics, computer science, and cognitive sciences. Notably, it is not a straightforward task to map the human’s brain reasoning into computer processes. In this paper, we propose to facilitate such mapping by investigating a key element, which is to identify the step-by-step formation of perceptual judgments. Herein, we first introduce an approach that employs general type-2 fuzzy logic to dynamically model the human perceptions based on the human experience. This approach can be regarded as a step to enable the CWW vision. We have deployed the proposed approach in real-world settings and we will present two sets of real-world experiments which were conducted in the intelligent apartment (iSpace) in the University of Essex. The first set of experiments demonstrates the results of the proposed approach for the adaptive modeling of ambient luminance perception. In the second set of experiments, we show that our approach performs better in the rule base evaluation processing time and in output accuracy with comparison to an interval type-2 fuzzy logic system.     

Robots, Dennett and the autonomous: a terminological investigation

In the present enterprise we take a look at the meaning of Autonomy, how the word has been employed and some of the consequences of its use in the sciences of the artificial. Could and should robots really be autonomous entities? Over and beyond this, we use concepts from the philosophy of mind to spur on enquiry into the very essence of human autonomy. We believe our initiative, as does Dennett's life-long research, sheds light upon the problems of robot design with respect to their relation with humans.     

Are Turing Machines Platonists? Inferentialism and the Computational Theory of Mind

We first discuss Michael Dummett’s philosophy of mathematics and Robert Brandom’s philosophy of language to demonstrate that inferentialism entails the falsity of Church’s Thesis and, as a consequence, the Computational Theory of Mind. This amounts to an entirely novel critique of mechanism in the philosophy of mind, one we show to have tremendous advantages over the traditional Lucas-Penrose argument.     

Being aware: where we think the action is

The term awareness has become one of the core concepts in human (computer-) interaction. By awareness we usually try to describe a human’s capability of perception and the cognitive effort related to an apperception task as well as similar abilities of a computer system to act sensitively with respect to context. But what does it mean to be aware in or of some context? Are not all things assembled in a system affected by being in that system—being aware of it or not? What does it take to be aware and what are the consequences of being not aware? This article discusses recent paradigms of computer science in the context of philosophy of mind, psychology of perception and sociology to shed light on awareness, context, perception and affection. The conclusion that is drawn is that any observation is inherently predetermined by our model of the world: the meaning of data we collect is determined by the model assumptions under which the observer is running.     

Hypercalculia for the mind emulation

By imitating the high-speed computational behavior of a machine through a consciousness of the future, we suggest a reverse artificial intelligence in an attempt to achieve the computational whole mind emulation of high level thoughts. The methodology, using such reverse artificial intelligence which we run with control on the mind instead of a machine, is disclosed. We then generalize this ability to enable the proposed mind emulation through high-speed mental computation processes. We suggest a set of theoretical and empirical principles and methods for the mind transfer, which leads to an almost unlimited potential for the human beings and society. In this paper, we present the most basic case of experimenting with the inactive behaviors, then a new hypothesis.