多模态视觉语言表征学习研究综述

我们生活在一个由大量不同模态内容构建而成的多媒体世界中,不同模态信息之间具有高度的相关性和互补性,多模态表征学习的主要目的就是挖掘出不同模态之间的共性和特性,产生出可以表示多模态信息的隐含向量.主要介绍了目前应用较广的视觉语言表征的相应研究工作,包括传统的基于相似性模型的研究方法和目前主流的基于语言模型的预训练的方法....     

Integrating Multiple Learning Strategies in First Order Logics

This paper describes a representation framework that offers a unifying platform for alternative systems, which learn concepts in First Order Logics. The main aspects of this framework are discussed. First of all, the separation between the hypothesis logical language (a version of the VL21 language) and the representation of data by means of a relational database is motivated. Then, the functional layer between data and hypotheses, which makes the data accessible by the logical level through a set of abstract properties is described. A novelty, in the hypothesis representation language, is the introduction of the construct of internal disjunction; such a construct, first used by the AQ and Induce systems, is here made operational via a set of algorithms, capable to learn it, for both the discrete and the continuous-valued attributes case. These algorithms are embedded in learning systems (SMART+, REGAL, SNAP, WHY, RTL) using different paradigms (symbolic, genetic or connectionist), thus realizing an effective integration among them; in fact, categorical and numerical attributes can be handled in a uniform way. In order to exemplify the effectiveness of the representation framework and of the multistrategy integration, the results obtained by the above systems in some application domains are summarized.     

Interoperability for Elearning Services Management and Provision

Learning Objects offer flexibility and adaptability for users to request personalised information for learning. There are standards to guide the development of learning objects. However, individual developers may customise these standards for serving different purposes when defining, describing, managing and providing learning objects, which are normally stored in heterogeneous repositories. Barriers to interoperability hinder sharing of learning services and subsequently affect quality of instructional design as learners expect to be able to receive their personalised learning content. All these impose difficulties to the users in getting the right information from the right sources. This paper investigates the interoperability issues in elearning services management and provision and presents an approach to resolve interoperability at three levels.     

基于小样本度量迁移学习的表面缺陷检测

将小样本学习中的度量学习方法引入缺陷检测领域,提出小样本度量迁移学习方法,用于解决深度学习方法中需要大量学习样本的问题.方法主要分为两个阶段:第一阶段使用公开或便于获得的大型数据集预训练深度网络;第二阶段将网络学习到的相关知识通过度量学习模块迁移到表面缺陷检测领域.实验表明,小样本学习在缺陷检测领域的可行性.     

一种形式化的学习过程建模

目前对E-learning技术进行深入的研究对于丰富我国教育方式和提高总体教育水平有着重要的意义。学习过程的建模则是为实现学习管理系统,将E-learning的相关理念运用于实际,打下坚实的理论基础。本文首先介绍了学习设计理念以及Petri网的概念。其次,依次描述了学习活动和活动构件、技能、学习过程的建模过程,并在在此基础上补充了活动结构的概念。最后,对学习过程建模在学习管理系统中的应用提出了展望。     

基于模型的机器人强化学习研究综述

基于模型的强化学习通过学习一个环境模型和基于此模型的策略优化或规划,实现机器人更接近于人类的学习和交互方式.文中简述机器人学习问题的定义,介绍机器人学习中基于模型的强化学习方法,包括主流的模型学习及模型利用的方法.主流的模型学习方法具体介绍前向动力学模型、逆向动力学模型和隐式模型.模型利用的方法具体介绍基于模型的规划、...     

Appropriate media choice for e-learning effectiveness: Role of learning domain and learning style

As the number of online education and training programs increase, researchers and practitioners are interested in investigating ways to design and develop effective e-learning programs. One of the major design decisions that affects learning effectiveness is the choice of media to present the contents of such programs. The prevailing tendency seems to be to use “richer” medium, in the progression from text to graphics to audio to video, for designing and developing e-learning programs. It is not clear, however, if a “richer” medium provides proportionately higher learning effectiveness. To investigate this gap in our understanding, we developed an integrated research model and tested it empirically. Our results showed that the relationship between media choice in an e-learning program and the effectiveness of that program is moderated by the learning domain of the program and the learning styles of learners.     

Learning equilibrium as a generalization of learning to optimize

We argue that learning equilibrium is an appropriate generalization to multi-agent systems of the concept of learning to optimize in single-agent setting. We further define and discuss the concept of weak learning equilibrium.     

Performance and human factors: considerations about cognition and attention for self-paced and externally-paced events

The cognitive psychology school of thought has spawned models of sequential stages or phases of information processing associated with various tasks. It has encouraged the study of cognitions and attention as related to learning, performance and high levels of achievement in goal-directed complex activities in which movement is the medium of expression. Although more recently proposed dynamical systems models challenge the simplicity of this approach, there is little doubt that the ability to learn as well as to excel in performing movement skills depends to a great degree on the effective self-regulation of cognitive processes in a variety of situations. What to think about (or not think about) prior to, during and even after an event can have great consequences on present and subsequent performance. Relevant externally-provided and selfgenerated strategies should enable these processes to function at an optimal level, and are the subject of an increasing amount of research. For such purposes, it is convenient to categorize events as self-paced (closed) and externally-paced (open). Examples of both types of events exist in sport as well as in various occupations and recreational activities, with different information processing demands associated with each one. Any breakdown in a particular stage of processing will potentially lead to poorer performance. Special training techniques and strategies are evolving from the cognitive and psychophysiological research literature that might improve the level of functioning at each stage for either self-paced or externally-paced skills.     

基于二次学习的半监督字典学习软件缺陷预测*

当软件历史仓库中有标记训练样本较少时,有效的预测模型难以构建.针对此问题,文中提出基于二次学习的半监督字典学习软件缺陷预测方法.在第一阶段的学习中,利用稀疏表示分类器将大量无标记样本通过概率软标记标注扩充至有标记训练样本集中.再在扩充后的训练集上进行第二阶段的鉴别字典学习,最后在学得的字典上预测缺陷倾向性.在NASA MDP和PROMISE AR数据集上的实验验证文中方法的优越性.     

案例教学与适应性学习之初探

以适应性学习为基础,提出了在自适应性学习(Adaptive Learning)中如何将案例教学(Case-based Learning)融入其中,在学习中如何对学习进行评价,并根据评价为学习者提供与其相适应的案例,让学习者在情境中学习,使得学习更加高效可行。     

Curriculum Reform of Programming and Algorithm Foundation for Competency-based Learning

It is important to transform knowledge-based learning to competency-based learning. This paper describes the exploration and practice of "programming and algorithm foundation" curriculum reform for competency-based learning. In order to cultivate students' ability of high-level program development, the intelligent learning system of "MOOC/SPOC + icoding online experiment and programming ability test Platform + Rain Classroom" is established. In the case of limited class hours, we make full use of online resources to build a student-centered method to internalize knowledge and ability. We guide students to complete the basic knowledge module of MOOC or SPOC, and complete the programming experiment on icoding platform. According to the feedback of learning outcome, teachers use offline classroom and rain classroom to sort out the key and difficult points, expanding the depth and breadth of the curriculum, and stimulate students' enthusiasm to participate in the curriculum.     

基于半监督学习的增量图像分类方法

为有效使用大量未标注的图像进行分类,提出一种基于半监督学习的图像分类方法。通过共同的隐含话题桥接少量已标注的图像和大量未标注的图像,利用已标注图像的Must-link约束和Cannot-link约束提高未标注图像分类的精度。实验结果表明,该方法有效提高Caltech-101数据集和7类图像集约10%的分类精度。此外,针对目前绝大部分半监督图像分类方法不具备增量学习能力这一缺点,提出该方法的增量学习模型。实验结果表明,增量学习模型相比无增量学习模型提高近90%的计算效率。关键词半监督学习,图像分类,增量学习中图法分类号TP391。41IncrementalImageClassificationMethodBasedonSemi-SupervisedLearningLIANGPeng^1,2,LIShao-Fa²,QINJiang-Wei²,LUOJian-Gao³¹(SchoolofComputerScienceandEngineering,GuangdongPolytechnicNormalUniversity,Guangzhou510665)²(SchoolofComputerScienceandEngineering,SouthChinaUniversityofTechnology,Guangzhou510006)³(DepartmentofComputer,GuangdongAIBPolytechnicCollege,Guangzhou510507)ABSTRACTInordertouselargenumbersofunlabeledimageseffectively,animageclassificationmethodisproposedbasedonsemi-supervisedlearning。Theproposedmethodbridgesalargeamountofunlabeledimagesandlimitednumbersoflabeledimagesbyexploitingthecommontopics。Theclassificationaccuracyisimprovedbyusingthemust-linkconstraintandcannot-linkconstraintoflabeledimages。TheexperimentalresultsonCaltech-101and7-classesimagedatasetdemonstratethattheclassificationaccuracyimprovesabout10%bytheproposedmethod。Furthermore,duetothepresentsemi-supervisedimageclassificationmethodslackingofincrementallearningability,anincrementalimplementationofourmethodisproposed。Comparingwithnon-incrementallearningmodelinliterature,theincrementallearningmethodimprovesthecomputationefficiencyofnearly90%。     

移动学习对MOOC学习行为与效果的影响研究

移动设备的普及使得学生的学习方式发生了根本性的变化。研究移动学习对学生的学习行为和学习效果的影响,有助于完善和改进大规模开放在线课程(MOOC)。本文采用定量研究分析方法对MOOC平台数据进行统计分析。结果表明,采用移动学习的学生对学习材料的参与度较高,并且完成课程学习的频率也较高。     

学习兴趣与主动学习的研究

现在高等学校的学生具有很强的社会的特点,现实性强,在具有众多学生的高等学校内要学生对学习有兴趣,这是一件难事。了解学生,让学生主动学习,靠教育工作者在办公室里是想不出好办法的,让学生参与教学活动,参与教学过程设计,这是提高学习兴趣,主动学习的唯一方法。     

基于决策树集成的偏标记学习算法*

为了克服偏标记学习中监督信息缺失的问题,根据偏标记样本的性质设计决策树生成过程中的样本分裂规则,改造决策树的建立算法.文中算法首先对样本进行bootstrap采样并建立多棵决策树,然后对各决策树结果进行投票得出最终预测结果.在人工数据集和真实数据集上的实验表明,文中算法具有较好的分类性能.     

基于Android移动学习平台研究

在移动互联网时代,为满足高等院校在校生随时随地进行学习,满足高校自身的线上线下课堂的需求,设计了一种基于Android平台的移动学习系统,该系统可以运行在基于Android系统的手机和平板电脑等终端上,能够进行线上课程学习,同时可以让师生进行在线交流。本系统对客户端与服务器端进行了详细的分析与设计,为移动学习平台的实现提供了有价值的参考模型。     

机器学习方法及其技术应用

描述了机器学习系统的基本结构模型，结合几种主要策略的基本思想，比较和分析了它们的优越性和各自的局限性，重点介绍了机器学习方法的技术应用。     

《网络安全》教学中学生自主学习能力的培养

针对《网络安全》课程的特点,为了激发学生的学习兴趣和创新精神,根据教学实践经验提出了《网络安全》教学中培养学生自主学习能力的相关策略。实践证明,在教学过程中加强学生自主学习能力的培养能达到更好的教学效果。     

深度学习技术在火灾图像识别中的应用

火灾事故频发严重威胁着社会公共安全和人们的生命财产安全。火灾发生的不可预见性增加了火灾防控的难度。传统温感、烟感火灾探测设备对室内空间火灾探测效率较高;以人工选择特征为依据的火灾图像识别技术受限于实际火灾场景特征复杂多变,存在误报情况;深度学习技术通过海量火灾场景图片训练和网络参数优化,自动提取火灾图像深度抽象特征,以达到对火灾的精准识别和预警判断。本文就火灾图像识别及深度学习技术在该领域中的应用进行分析,对影响深度学习技术在火灾图像识别应用中的瓶颈问题进行探讨,并展望了该技术的未来发展。