Particularism and the Classification and Reclassification of Moral Cases

Is it possible to learn to classify cases as morally acceptable or unacceptable without using moral principles? Jonathan Dancy has suggested that moral reasoning (including learning) could be done without moral principles, and he has suggested that neural network models could aid in understanding how to do this. This article explores Dancy's suggestion by presenting a neural network model of case classification. The author argues that although some nontrivial case classification might be possible without the explicitly consulting or executing moral principles, the process of reclassifying cases is best explained by using moral principles.This article is part of a special issue on Machine Ethics.     

Moral Gridworlds: A Theoretical Proposal for Modeling Artificial Moral Cognition

Minds and Machines - I describe a suite of reinforcement learning environments in which artificial agents learn to value and respond to moral content and contexts. I illustrate the core principles...     

比喻法、类比法在网络技术基础课程教学中的应用

该文对中职计算机专业学生学习计算机网络基础课程的必要性和教学方法进行了探讨.比喻,类比教学法是提高网络技术基础课程教学效果的有效途径.通过生动教学案例论述了比喻,类比教学法在网络技术基础课程教学的具体应用.     

Computation, Implementation, Cognition

Putnam (Representations and reality. MIT Press, Cambridge, 1988) and Searle (The rediscovery of the mind. MIT Press, Cambridge, 1992) famously argue that almost every physical system implements every finite computation. This universal implementation claim, if correct, puts at the risk of triviality certain functional and computational views of the mind. Several authors have offered theories of implementation that allegedly avoid the pitfalls of universal implementation. My aim in this paper is to suggest that these theories are still consistent with a weaker result, which is the nomological possibility of systems that simultaneously implement different complex automata. Elsewhere I (Shagrir in J Cogn Sci, 2012) argue that this simultaneous implementation result challenges a computational sufficiency thesis (articulated by Chalmers in J Cogn Sci, 2012). My focus here is on theories of implementation. After presenting the basic simultaneous implementation construction, I argue that these theories do not avoid the simultaneous implementation result. The conclusion is that the idea that the implementation of the right kind of automaton suffices for a possession of a mind is dubious.     

Reverse Psychologism,Cognition and Content

The confusion between cognitive states and the content of cognitive states that gives rise to psychologism also gives rise to reverse psychologism. Weak reverse psychologism says that we can study cognitive states by studying content – for instance, that we can study the mind by studying linguistics or logic. This attitude is endemic in cognitive science and linguistic theory. Strong reverse psychologism says that we can generate cognitive states by giving computers representations that express the content of cognitive states and that play a role in causing appropriate behaviour. This gives us strong representational, classical AI (REPSCAI), and I argue that it cannot succeed. This is not, as Searle claims in his Chinese Room Argument, because syntactic manipulation cannot generate content. Syntactic manipulation can generate content, and this is abundantly clear in the Chinese Room scenano. REPSCAI cannot succeed because inner content is not sufficient for cognition, even when the representations that carry the content play a role in generating appropriate behaviour.     

Emotion,Cognition and Artificial Intelligence

Some have claimed that since machines lack emotional “qualia”, or conscious experiences of emotion, machine intelligence will fall short of human intelligence. I examine this objection, ultimately finding it unpersuasive. I first discuss recent work on emotion (from cognitive science, neuroscience and philosophy) that suggests that emotion plays various roles in cognition. I then raise the following question: are phenomenal experiences of emotion an essential or necessary component of the performance of these cognitive abilities? I then sharpen the question by distinguishing between four possible positions one might take. I reject one of these four positions largely on empirical grounds. But the remaining three positions all suggest that even if emotional qualia play an important role in human cognition, emotional qualia are not essential to the performance of these cognitive abilities in principle, so, e.g., a machine that lacks emotional qualia might still be able to perform them.     

微机电系统的研究与分析

详细介绍了微机械电子系统的内涵.内容包括微型传感器、微型执行器等研究领域.还介绍了微机械电子系统加工工艺,阐明了其涉及的科学技术问题,对信息MEMS用途及发展趋势做了较详尽的讨论.     

Jules Davidoff,Cognition through Color,Issues in the Biology of Language and Cognition Series

Minds and Machines -     

Segmented Animation,User-Control Strategy and Cognition

The aim of this study was to investigate the effects of various user-control strategies of segmented animation in learning abstract contents or processes that are not naturally visual on the cognition of students. In particular, the study examined the effects of five different user-control strategies: linear user-control, random user-control, free user-control, program-control, and continuous user-control. The research design was quasi-experimental and the data obtained were statistically analysed using ANCOVA and ANOVA. The instruments involved were pre-test, post-test, and NASA-TLX cognitive load test. The sample size consisted of 265 semester-two students enrolled in the Diploma in Networking System. The results indicated significant differences in the post-test and cognitive load test outcomes. In conclusion, this study suggests that the use of user-control, either linear user-control or random user-control, were sufficient strategies for learning abstract contents in segmented animation form.     

Derivational Analogy in PRODIGY: Automating Case Acquisition,Storage, and Utilization

Expertise consists of rapid selection and application of compiled experience. Robust reasoning, however, requires adaptation to new contingencies and intelligent modification of past experience. And novel or creative reasoning, by its real nature, necessitates general problem-solving abilities unconstrained by past behavior. This article presents a comprehensive computational model of analogical (case-based) reasoning that transitions smoothly between case replay, case adaptation, and general problem solving, exploiting and modifying past experience when available and resorting to general problem-solving methods when required. Learning occurs by accumulation of new cases, especially in situations that required extensive problem solving, and by tuning the indexing structure of the memory model to retrieve progressively more appropriate cases. The derivational replay mechanism is discussed in some detail, and extensive results of the first full implementation are presented. These results show up to a large performance improvement in a simple transportation domain for structurally similar problems, and smaller improvements when less strict similarity metrics are used for problems that share partial structure in a process-job planning domain and in an extended version of the strips robot domain.     

The Analogy Between Electrical Networks and Flowcharts

A recently proposed analogy between discrete systems and flowcharts is discussed. It is pointed out that the analog of Kirchhoff's voltage law does not apply to flowcharts, and that the analogy is likely to be of limited value as an aid to program analysis.     

Interactive Concept-Learning and Constructive Induction by Analogy

The available concept-learners only partially fulfill the needs imposed by the learning apprentice generation of learners. We present a novel approach to interactive concept-learning and constructive induction that better fits the requirements imposed by the learning apprentice paradigm. The approach is incorporated in the system Clint-Cia, which integrates several user-friendly features into one working whole: it is interactive, generates examples, shifts its bias, identifies concepts in the limit, copes with indirect relevance, recovers from errors, performs constructive induction and invents new concepts by analogy to previously learned ones.     

基于SVM的中文类比检索方法

随着互联网的不断发展,用户因不能准确输入查询关键字而无法准确获取未知领域信息的问题日益严重。作为一种根据已知领域知识获取未知领域知识的全新检索方式,类比检索逐渐成为研究热点。类比检索通过分析词对之间的潜在关系而准确地返回目标信息。例如,给定类比查询请求Q={A:B,C:?},A与B之间具有某种潜在关系,类比检索的目标是得到?所代表的目标词(集)D,其中A与B的关系和C与D的潜在关系相似。类比检索的两个难点是潜在关系挖掘和目标词抽取,这两个问题对于中文而言,更具挑战性。提出了基于SVM的中文类比检索方法 (SVM based Chinese Analogy Retrieval,SVMbCAR)。该方法的两个主要成分包括基于SVM的关系代表词抽取和目标词确定。基于真实测试数据集(包含源自人立方的600个人物实体对)的实验表明,SVMbCAR方法抽取关系代表词的准确率为82.3%,抽取目标词的准确率为90.5%。     

Estimating Maintenance Effort by Analogy

Effort estimation is a key step of any software project. This paper presents a method to estimate project effort using an improved version of analogy. Unlike estimation methods based on case-based reasoning, our method makes use of two nearest neighbors of the target project for estimation. An additional refinement based on the relative location of the target project is then applied to generate the effort estimate. We first identify the relationships between cost drivers and project effort, and then determine the number of past project data that should be used in the estimation to provide the best result. Our method is then applied to a set of maintenance projects. Based on a comparison of the estimation results from our estimation method and those of other estimation methods, we conclude that our method can provide more accurate results.     

Analogy in Inductive Theorem Proving

In this paper, we investigate analogy-driven proof plan construction in inductive theorem proving. The intention is to produce a plan for a target theorem that is similar to a given source theorem. We identify second-order mappings from the source to the target that preserve induction-specific proof- relevant abstractions dictating whether the source plan can be replayed. We replay the planning decisions taken in the source if the reasons or justifications for these decisions still hold in the target. If the source and target plan differ significantly at some isolated point, additional reformulations are invoked to add, delete, or modify planning steps. These reformulations are not ad hoc but are triggered by peculiarities of the mappings and by failed justifications. Employing analogy on top of the proof planner CLAM has extended the problem-solving horizon of CLAM: With analogy, some theorems could be proved automatically that neither CLAM nor NQTHM could prove automatically.     

《数据结构》的类比教学

针对数据结构课程内容多、逻辑性强、概念抽象等特点,从“横向”的存储类比和不同事物间的“纵向”类比两个角度介绍了数据结构的类比教学,由此及彼,化抽象为具体,帮助学生记忆和理解抽象概念与算法,激发学生的学习热情,提高了课堂教学效果。