Cognitive agents and machine learning by example: Representation with conceptual graphs

As machine learning (ML) and artificial intelligence progress, more complex tasks can be addressed, quite often by cascading or combining existing models and technologies, known as the bottom‐up design. Some of those tasks are addressed by agents, which attempt to simulate or emulate higher cognitive abilities that cover a broad range of functions; hence, those agents are named cognitive agents. We formulate, implement, and evaluate such a cognitive agent, which combines learning by example with ML. The mechanisms, algorithms, and theories to be merged when training a cognitive agent to read and learn how to represent knowledge have not, to the best of our knowledge, been defined by the current state‐of‐the‐art research. The task of learning to represent knowledge is known as semantic parsing, and we demonstrate that it is an ability that may be attained by cognitive agents using ML, and the knowledge acquired can be represented by using conceptual graphs. By doing so, we create a cognitive agent that simulates properties of “learning by example,” while performing semantic parsing with good accuracy. Due to the unique and unconventional design of this agent, we first present the model and then gauge its performance, showcasing its strengths and weaknesses.     

Robot Programming by Demonstration (RPD): Supporting the Induction by Human Interaction

Machine Learning - Programming by Demonstration (PbD) is a programming method that allows software developers to add new functionalities to a system by simply showing them in the form of few...     

冰雹猜想的计算机编程证明

冰雹猜想是一个风靡全球的趣味数学游戏。迄今为止,人们还未能得到这个猜想在数学上的严格证明。可以利用计算机强大的计算能力,根据冰雹猜想的计算规律,编写程序让计算机来证明冰雹猜想的正确性。程序的设计思想是先证明任意一个数的正确性,再证明某个数据区间内所有数据的正确性,通过程序的运行,对一定范围内的所有自然数进行验证,从而证明了冰雹猜想。     

程序设计教学的“圈养”与“放养”

本文从程序设计教学和饲养畜禽的相似谈起．阐述了在程序设计教学中如何运用“圈养”和“放养”两种方式实施教学。以及两种教学方式下多种具体的教学方法。     

《C语言程序设计》的教学体会

《C语言程序设计》是计算机专业的第一门计算机编程语言课程,对今后的编程语言学习进行非常重要作用,因此应该加强对《C语言程序设计》课程的教学。通过教学过程的实践,总结了一些教学体会和教学方法,以促进该课程的教学和学习。     

Learning from video modeling examples: Effects of seeing the human model's face

Video modeling examples in which a human(-like) model shows learners how to perform a task are increasingly used in education, as they have become very easy to create and distribute in e-learning environments. However, little is known about design guidelines to optimize learning from video modeling examples. Given that the human face is known to capture observers' attention, the question addressed in this study is whether seeing the model's face in the video would help or hinder learning. Participants twice studied a video modeling example in which a problem-solving task was demonstrated and in which the model's face was either visible or not, and after each view they attempted to solve the problem themselves. Their eye movement data were recorded while watching the video examples. Results show better performance after observing the second example in the condition that did see the model's face.     

项目教学法在面向对象程序设计课程教学中的应用

面向对象程序设计是高校计算机类专业大学生的必修课。本文结合本科教学实际,针对目前该门课程教学中存在的问题,提出项目教学法在教学中的应用,并从准备到实施的各个环节对项目教学法进行论述,同时对项目教学法和传统教学法进行分析比较。     

“SDSPR教学法”在程序设计类课程中的应用

本文详细介绍了SDSPR教学方法的五个环节,并总结了SDSPR教学方法的特点,说明了"SDSPR"教学方法在程序设计类课程中的重要作用,对于推行"理论实践一体化"的教学模式和提高高职软件专业学生的编程技能具有重要的意义。     

C语言程序设计课程教学方法的改革与实践

C语言程序设计是信息与计算科学专业一门重要且难度很大的专业必修课。为解决C语言教学中的重点和难点,作者结合多年的教学经验,从三个方面对教学方法的改进进行了讨论,以期提高教学效果。     

任务驱动法在JAVA程序设计课程中的应用

在《Java程序设计》课程教学中,以激发学生学习兴趣为前提,提高学生的自主学习能力为目标,引导学生积极主动参与学习,成为真正的学习主体,最终使学生将知识转化为能力是现代高教改革的主流。那么,与该理念相适应的教学方法就显得特别重要。将任务驱动法应用于该课程可以很好地调动学生的学习积极性,实践表明学生的程序设计能力得到极大的提高。     

Different roles and mutual dependencies of data, information, and knowledge — An AI perspective on their integration

The unclear distinction between data, information, and knowledge has impaired their combination and utilization for the development of integrated systems. There is need for a unified definitional model of data, information, and knowledge based on their roles in computational and cognitive information processing. An attempt to clarify these basic notions is made, and a conceptual framework for integration is suggested by focusing on their different roles and frames of reference within a decision-making process. On this basis, ways of integrating the functionalities of databases, information systems and knowledge-based systems are discussed by taking a knowledge level perspective to the analysis and modeling of systems behaviour. Motivated by recent work in the area of case-based reasoning related to decision support systems, it is further shown that a specific problem solving episode, or case, may be viewed as data, information, or knowledge, depending on its role in decision making and learning from experience. An outline of a case-based system architecture is presented, and used to show that a focus on the retaining and reuse of past cases facilitates a gradual and evolutionary transition from an information system to a knowledge-based system.     

3D Scene interpretation by combining probability theory and logic: The tower of knowledge

We explore a newly proposed system architecture, called tower of knowledge (ToK), in the context of labelling components of building scenes. The ToK architecture allows the incorporation of statistical feature distributions and logic rules concerning the definition of a component, within a probabilistic framework. The maximum likelihood method of label assignment is modified by being multiplied with a function, called utility function, that expresses the information coming from the logic rules programmed to the system. The logic rules are designed to define an object/component by answering the questions “why” and “how”, referring to the actions in which a particular object may be observed to participate and the characteristics it should have in order to be able to participate in these actions. Two sets of measurements are assumed to be available: those made initially for all components routinely, and which supply the initial statistically based inference of possible labels of each component, and those that are made in order to confirm or deny a particular characteristic of the component that would allow it to participate in a specific action. A recursive version of the architecture is also proposed, in which the distributions of the former types of measurement may be learnt in the process, having no training data at all. Multi-view images are used as input to the system, which uses standard techniques to build the 3D models of the buildings. The system is tested on labelling the components of 10 3D models of buildings. The components are identified either manually, or fully automatically. The results are compared with those obtained by expandable Bayesian networks. The recursive version of ToK proves to be able to cope very well even without any training data, where it learns the characteristics of the various components by simply applying the pre-programmed logic rules that connect labels, actions and attributes.     

J2EE方向Web程序设计实训课程教学内容体系的建立

该文分析了高职高专院校软件技术专业学生的Web程序设计实训课程的特点,提出了Web程序设计实训课程内容设计的原则．建立了课程的教学内容体系。     

Programming assistance tools to support the learning of IT programming in South African secondary schools

Novice programmers struggle to understand introductory programming concepts and this difficulty, associated with learning to program, contributes mainly to the lack of interest in the field of Computer Science at tertiary level. Programming assistance tools have been used to assist novice programmers extensively at education institutions. A programming assistance tool (PAT) is a software program that can be used by novice programmers to learn how to program and/or improve their understanding of programming concepts.This research proposes that novice programmers, specifically Information Technology (IT) scholars in South African secondary schools, could be supported by PATs. The main objective of this research was to determine whether the use of a PAT impacted IT scholars' understanding of programming concepts and their motivation towards programming in general. Criteria for the selection of PATs were derived from the programming difficulties identified in literature and from surveys to IT teachers and scholars. The selection criteria were grouped into programming knowledge and programming skills categories. Existing PATs were evaluated using the selection criteria and three PATs, namely, RoboMind, Scratch and B#, were selected for evaluation in this research study. A convenience sample of schools participated in the study. The three PATs provided different approaches while being able to support the Delphi programming language used in schools that participated in the study.The findings of this research indicated that, although scholars perceived the PATs to be useful in the explanation of certain of the programming concepts, there was no conclusive evidence that IT scholars who used a PAT had a significantly better understanding of programming concepts and motivation towards programming than scholars who did not use a PAT. Participant feedback was used to identify the strengths and shortcomings of the three PATs and to provide recommendations for the development of future PATs specifically designed to support IT scholars.     

On the Approximation of Stochastic Concurrent Constraint Programming by Master Equation

We explore the relation between the stochastic semantic associated to stochastic Concurrent Constrain Programming (sCCP) and its fluid-flow approximation. Writing the master equation for a sCCP model, we can show that the fluid flow equation is a first-order approximation of the true equation for the average. Moreover, we introduce a second-order correction and first-order equations for the variance and the covariance.     

Complementary computing: policies for transferring callers from dialog systems to human receptionists

We describe a study of the use of decision-theoretic policies for optimally joining human and automated problem-solving efforts. We focus specifically on the challenge of determining when it is best to transfer callers from an automated dialog system to human receptionists. We demonstrate the sensitivities of transfer actions to both the inferred competency of the spoken-dialog models and the current sensed load on human receptionists. The policies draw upon probabilistic models constructed via machine learning from cases that were logged by a call routing service deployed at our organization. We describe the learning of models that predict outcomes and interaction times and show how these models can be used to generate expected-utility policies that identify when it is best to transfer callers to human operators. We explore the behavior of the policies with simulations constructed from real-world call data. See D’Agostino (2005) for a reflection from the business community about the failure to date of automated speech recognition systems to penetrate widely.     

J2EE方向Web程序设计实训课程教学内容体系的建立

该文分析了高职高专院校软件技术专业学生的Web程序设计实训课程的特点,提出了Web程序设计实训课程内容设计的原则,建立了课程的教学内容体系。     

Fostering historical knowledge and thinking skills using hypermedia learning environments: The role of self-regulated learning

In this study, we examined how high-school students utilized a hypermedia learning environment (HLE) to acquire declarative knowledge of a historical topic, as well as historical thinking skills. In particular, we were interested in whether self-regulated learning (SRL; Winne & Hadwin, 1998; Zimmerman, 2000) processing was related to the acquisition of declarative knowledge and historical thinking. We found that, using the HLE, participants did learn from pretest to posttest, and that they most often engaged in strategy use SRL processes. However, the frequency of participant use of planning SRL processes, not strategy use, was predictive of learning. This study has implications for how educators use HLEs to foster historical thinking skills, and suggests that scaffolding planning skills may facilitate students’ use of computers as cognitive and metacognitive tools for learning (Azevedo, 2005; Lajoie, 2000).     

The State of the Art in Enhancing Trust in Machine Learning Models with the Use of Visualizations

Machine learning (ML) models are nowadays used in complex applications in various domains, such as medicine, bioinformatics, and other sciences. Due to their black box nature, however, it may sometimes be hard to understand and trust the results they provide. This has increased the demand for reliable visualization tools related to enhancing trust in ML models, which has become a prominent topic of research in the visualization community over the past decades. To provide an overview and present the frontiers of current research on the topic, we present a State-of-the-Art Report (STAR) on enhancing trust in ML models with the use of interactive visualization. We define and describe the background of the topic, introduce a categorization for visualization techniques that aim to accomplish this goal, and discuss insights and opportunities for future research directions. Among our contributions is a categorization of trust against different facets of interactive ML, expanded and improved from previous research. Our results are investigated from different analytical perspectives: (a) providing a statistical overview, (b) summarizing key findings, (c) performing topic analyses, and (d) exploring the data sets used in the individual papers, all with the support of an interactive web-based survey browser. We intend this survey to be beneficial for visualization researchers whose interests involve making ML models more trustworthy, as well as researchers and practitioners from other disciplines in their search for effective visualization techniques suitable for solving their tasks with confidence and conveying meaning to their data.