增量式解释学习算法EBG—plus

传统的解释学习是通过单个实例进行学习的，学习结果往往带有实例本身的特殊性质，知识求精能较正这一缺陷，但学习结果的效用不高。本结合了ＥＢＬ方法和求精算法，提出了综合多个实例的增量式解释学习算法ＥＢＧ－ｐｌｕｓ，学习质量随实例数目增加而单调上升，学习结果效用高，并能够自动改进领域知识的编码质量。     

对领域理论不完善问题的描述,分类与处理

本文对解释学习中基于规则的领域理论和解释过程进行了描述，并给出解释学习中不完善问题的分类，分析了解释学习中领域理论不完全现象，推导出若干性质，论述了在不完全的解释中存在形式上最佳的修改方案，提出一个解决不完全问题的进行解释的学习算法。     

增量式解释学习算法EBG—plus*

传统的解释学习(EBL)是通过单个实例进行学习的，学习结果往往带有实例本身的特殊性质,知识求精能较正这一缺陷，但学习结果的效用不高．本文结合了EBL方法和求精算法，提出综合多个实例的增量式解释学习算法EBG—plus，学习质量随实例数目增加而单调上升，学习结果效用高，并能够自动改进领域知识的编码质量．     

解释学习中模糊概念的学习

本文提出了一种模糊知识的表示模式，给出了在模糊意义下的基于解释的学习的一种描述，以及解释、学习机制，使在解释学习中能够学习到一些带有模糊修饰词的新概念．本文描述形式同算子模糊逻辑而语义与其不同．     

一种解释学习系统的模型EBL／GA

解释学习是演绎式学习方法，而遗传算法是归纳式学习方法。本文提出的解释学习系统模型ＥＢＬ／ＧＡ，结合两者的优点提高了系统的效用。     

解释学习进展

本文对解释学习近期的研究进行了论述,包括解释学习机制,当前解释学习研究的几个重要问题:如可操作性的形式化定义、典型解释学习过程的解释与概括、针对不完善领域理论的多种解决办法等,还就解释学习特点、总体发展状况及今后研究方向提出了看法。     

适应噪声环境的解释学习算法

在现实世界里，ＡＩ系统难免受到噪声的影响．系统有效工作与否取决于它对噪声的敏感性如何．解释学习ＥＢＬ（ｅｘｐｌａｎａｔｉｏｎ－ｂａｓｅｄｌｅａｒｎｉｎｇ）也不例外．本文探讨了在例子受到噪声影响的情况下，解释学习的处理问题，提出了一个算法ＮＲ－ＥＢＬ（ｎｏｉｓｅ－ｒｅｓｉｓｔａｎｔＥＢＬ）．与现有的解释学习方法不同，ＮＲ－ＥＢＬ在训练例子含有噪声时仍然可以学习，以掌握实际的问题分布；和类似的工作不同，ＮＲ－ＥＢＬ指出了正确识别概念对于噪声规律的依赖性，试图从训练例子集合发现和掌握噪声的规律．可以相信，在识别概念时，借助于对噪声规律的认识，ＮＲ－ＥＢＬ可比ＥＢＬ和类似工作有更高的识别率．ＮＲ－ＥＢＬ是解释学习和统计模式识别思想的结合．它把现有的解释学习模型推广到例子含有噪声的情形，原来的ＥＢＬ算法只是它的特例．     

解释学习的效用问题

近年来,在机器学习领域,基于解释的学习引起了广泛的兴趣。解释学习是一种演绎学习方法,根据领域理论对训练实例进行解释,经过推广后获得新的知识。从可操作性的角度看,解释学习并没有学到真正新的知识,只是一种知识转换,它把原先不可操作的概念描述转换为可操作的目标概念描述,而使系统的性能得以提高。但原来的可操作性定义并没有考虑到解释学习的效用(utility)问题,人们发现这样的解释学习并不总能提高系统的性能,而是在大多数情况下会使系统的行为比未经学习时更差,这使得效用问题与不完善理论问题一样成为解     

故障诊断专家系统的集成学习方法

本文提出了一种基于解释与实例学习的集成学习方法。     

《比较国共双方在抗日战争中的贡献》课件赏析

这是一个基于网络学习的历史探究课程教学设计（WebQuest），课件选择了抗日战争的一个研究性课题引导学生利用互联网搜索资料，进行分析、比较和举证，在这一学习过程中体验、感知、理解和解释历史，培养“论从史出”的历史学习理念，培养学生学习历史的兴趣和热情，学会从不同角度看问题，注意听取他人不同的观点，逐渐使自己的认识接近真实、客观和全面。     

融合注意力机制与多任务学习的DR分级模型

在糖尿病患者中,糖尿病视网膜病变（Diabetic Retinopathy,DR）是导致失明的主要原因。针对眼底图像中存在极难发现的微动脉瘤等微小病理特征的问题,提出了一种注意力机制模块。该模块通过融合特征图原本的特征信息与注意力单元得到的通道信息,为微小特征增加了网络的权重,再使用除操作去除特征图中的冗余信息,得到注意力机制特征作为双任务的输入;针对均方误差（Mean Square Error,MSE）损失难优化和交叉熵（Cross Entropy,CE）损失未考虑错分DR等级的代价,设计了多任务学习模块,加权融合了回归任务的MSE损失和分类任务的CE损失。基于这两个模块的设计,提出了融合注意力机制的多任务学习网络（Fusion of Attention mechanism and Multi-Tasking learning network,FAMT）。在kaggle数据集上的实验表明,FAMT网络在验证集上的Kappa比仅使用回归任务的网络高出了2%,比仅使用分类任务的网络提高了4%;FAMT网络在测试集上的Kappa比EfficientNet网络高出1%,比M2CNN网络高出了5%。     

Application of the cross entropy method to the GLVQ algorithm

This paper discusses an alternative approach to parameter optimization of well-known prototype-based learning algorithms (minimizing an objective function via gradient search). The proposed approach considers a stochastic optimization called the cross entropy method (CE method). The CE method is used to tackle efficiently the initialization sensitiveness problem associated with the original generalized learning vector quantization (GLVQ) algorithm and its variants. Results presented in this paper indicate that the CE method can be successfully applied to this kind of problem on real-world data sets. As far as known by the authors, it is the first use of the CE method in prototype-based learning.     

The effects of assessment design on academic dishonesty,learner engagement,and certification rates in MOOCs

Background

Massive Open Online Courses (MOOCs) have touted the idea of democratizing education, but soon enough, this utopian idea collided with the reality of finding sustainable business models. In addition, the promise of harnessing interactive and social web technologies to promote meaningful learning was only partially successful. And finally, studies demonstrated that many learners exploit the anonymity and feedback to earn certificates unethically. Thus, establishing MOOC pedagogical models that balance open access, meaningful learning, and trustworthy assessment remains a challenge that is crucial for the field to achieve its goals.

Objectives

This study analysed the influence of an MOOC assessment model, denoted the Competency Exam (CE), on learner engagement, the level of cheating, and certification rates. At its core, this model separates learning from for-credit assessment, and it was introduced by the MITx Biology course team in 2016.

Methods

We applied a learning analytics methodology to the clickstream data of the verified learners (N = 559) from four consecutive runs of an Introductory Biology MOOC offered through edX. The analysis used novel algorithms for measuring the level of cheating and learner engagement, which were developed in the previous studies.

Results and Conclusions

On the positive side, the CE model reduced cheating and did not reduce learner engagement with the main learning materials – videos and formative assessment items. On the negative side, it led to procrastination, and certification rates were lower.

Implications

First, the results shed light on the fundamental connection between incentive design and learner behaviour. Second, the CE provides MOOC designers with an ‘analytically verified’ model to reduce cheating without compromising on open access. Third, our methodology provides a novel means for measuring cheating and learner engagement in MOOCs.

     

An Exploration of Impact of Cognitive Elaboration on Learning in ISD Projects

Stakeholder learning has been considered crucial for effective participation and the success of information system development (ISD). However, little guidance has been offered as an operational method to facilitate learning in ISD settings. We argue that “cognitive elaboration” (CE) is a helpful strategy for developing effective learning in client–developer interactions in ISD efforts. Two types of learning are investigated: model-building (MB) and model-maintenance (MM). The current study investigated whether CE performed by stakeholders themselves in client–developer interaction led to their MB rather than MM learning. In addition, an alternative hypothesis has been explored: whether mere communication activities may induce learning. Fifty individuals in seven ongoing software development projects in four organizations were examined. For each project, two meetings in which clients and developers participated were observed. The empirical results demonstrated that stakeholders in an ISD process who have engaged in CE themselves are more likely to experience MB learning; and that mere communication does not account for MB learning. An insignificant link between CE and MM learning was found. This study deepens our understanding about IS–user interactions. Limitations of the current research and implications for future research are discussed.     

基于ListMLE排序学习方法的机器译文自动评价研究

机器翻译译文质量的自动评价是推动机器翻译技术快速发展的一条重要途径。该文提出了基于List-MLE 排序学习方法的译文自动评价方法。在此基础上,探讨引入刻画译文流利度和忠实度的特征,来进一步提高译文自动评价结果和人工评价结果的一致性。实验结果表明,在评价WMT11德英任务和IWSLT08 BTEC CE ASR任务上的多个翻译系统的输出译文质量时,该文提出的方法预测准确率高于BLEU尺度和基于RankSVM的译文评价方法。     

Classification-based objective functions

Backpropagation, similar to most learning algorithms that can form complex decision surfaces, is prone to overfitting. This work presents classification-based objective functions, an approach to training artificial neural networks on classification problems. Classification-based learning attempts to guide the network directly to correct pattern classification rather than using common error minimization heuristics, such as sum-squared error (SSE) and cross-entropy (CE), that do not explicitly minimize classification error. CB1 is presented here as a novel objective function for learning classification problems. It seeks to directly minimize classification error by backpropagating error only on misclassified patterns from culprit output nodes. CB1 discourages weight saturation and overfitting and achieves higher accuracy on classification problems than optimizing SSE or CE. Experiments on a large OCR data set have shown CB1 to significantly increase generalization accuracy over SSE or CE optimization, from 97.86% and 98.10%, respectively, to 99.11%. Comparable results are achieved over several data sets from the UC Irvine Machine Learning Database Repository, with an average increase in accuracy from 90.7% and 91.3% using optimized SSE and CE networks, respectively, to 92.1% for CB1. Analysis indicates that CB1 performs a fundamentally different search of the feature space than optimizing SSE or CE and produces significantly different solutions. Editor: Risto Miikkulainen     

基于跨模态实体信息融合的神经机器翻译方法

现有多模态机器翻译(Multi-modal machine translation, MMT)方法将图片与待翻译文本进行句子级别的语义融合. 这些方法存在视觉信息作用不明确和模型对视觉信息不敏感等问题, 并进一步造成了视觉信息与文本信息无法在翻译模型中充分融合语义的问题. 针对这些问题, 提出了一种跨模态实体重构(Cross-modal entity reconstruction, CER)方法. 区别于将完整的图片输入到翻译模型中, 该方法显式对齐文本与图像中的实体, 通过文本上下文与一种模态的实体的组合来重构另一种模态的实体, 最终达到实体级的跨模态语义融合的目的, 通过多任务学习方法将CER模型与翻译模型结合, 达到提升翻译质量的目的. 该方法在多模态翻译数据集的两个语言对上取得了最佳的翻译准确率. 进一步的分析实验表明, 该方法能够有效提升模型在翻译过程中对源端文本实体的忠实度.     

Parallel Reinforcement Learning: A Framework and Case Study

In this paper, a new machine learning framework is developed for complex system control, called parallel reinforcement learning. To overcome data deficiency of current data-driven algorithms, a parallel system is built to improve complex learning system by self-guidance. Based on the Markov chain (MC) theory, we combine the transfer learning, predictive learning, deep learning and reinforcement learning to tackle the data and action processes and to express the knowledge. Parallel reinforcement learning framework is formulated and several case studies for real-world problems are finally introduced.      

基于移动学习的学科主题学习资源设计研究

移动学习作为一种新型的学习方式正成为研究热点,而基于移动学习的学科主题学习资源相对缺乏。本文阐述了移动学习的概念及特点、主题学习、学科主题学习资源的理论基础,分析了基于移动学习的学科主题学习资源设计的基本原则,最后构建了基于移动学习的学科主题学习资源的设计框架。