Error-driven active learning in growing radial basis function networks for early robot learning

In this paper, we describe a new error-driven active learning approach to self-growing radial basis function networks for early robot learning. There are several mappings that need to be set up for an autonomous robot system for sensorimotor coordination and transformation of sensory information from one modality to another, and these mappings are usually highly nonlinear. Traditional passive learning approaches usually cause both large mapping errors and nonuniform mapping error distribution compared to active learning. A hierarchical clustering technique is introduced to group large mapping errors and these error clusters drive the system to actively explore details of these clusters. Higher level local growing radial basis function subnetworks are used to approximate the residual errors from previous mapping levels. Plastic radial basis function networks construct the substrate of the learning system and a simplified node-decoupled extended Kalman filter algorithm is presented to train these radial basis function networks. Experimental results are given to compare the performance among active learning with hierarchical adaptive RBF networks, passive learning with adaptive RBF networks and hierarchical mixtures of experts, as well as their robustness under noise conditions.     

Behavioral modeling based on cloud computing and target user recommendation for English cloud classroom

The English cloud classroom learning system provides a simple and effective way to access cloud-based training and learning materials. Student records based on behavioral modeling and interactive volume are assumed that the degree of student participation in the course measure. Previous studies, typically the frequency of student activities while ignoring temporary information. Analysis of Students' Activities in the course over time. According to the online classroom activity data, similar behavior change with time students are clustered. These results are three different groups. A large majority of inactive students. Another group to active throughout the students. However, a group of students to the event, but their activity will be reduced throughout the course. These student groups exhibit different performance. Overall students more active, the better the results. In addition to these general trends, also identified a trend of alternative courses that can be found, for example, becomes an active group of students in the course. It suggests that students' behavior is identified from a single course of conduct than the more complex, multi-mode learning activities course. More research is essential. In this study, investigated the Portuguese teachers 'views on classroom management, the relationship between self-off and the efficacy of teachers' and teachers' perception of classroom behavioral teachers' perception of time. Use mediator and moderator variables on the cloud classroom management, and teachers of English teachers perceive the relationship between classroom conditions were cheating process analysis.     

结合Tri-training半监督学习和凸壳向量的SVM主动学习算法*

为解决监督学习过程中难以获得大量带有类标记样本且样本数据标记代价较高的问题,结合主动学习和半监督学习方法,提出基于Tri-training半监督学习和凸壳向量的SVM主动学习算法.通过计算样本集的壳向量,选择最有可能成为支持向量的壳向量进行标记.为解决以往主动学习算法在选择最富有信息量的样本标记后,不再进一步利用未标记样本的问题,将Tri-training半监督学习方法引入SVM主动学习过程,选择类标记置信度高的未标记样本加入训练样本集,利用未标记样本集中有利于学习器的信息.在UCI数据集上的实验表明,文中算法在标记样本较少时获得分类准确率较高和泛化性能较好的SVM分类器,降低SVM训练学习的样本标记代价.     

一种基于内容图像检索的半监督和主动学习算法

为了提高图像检索中相关反馈算法的效率,提出了一种新的基于相关概率的主动学习算法SVMpr,并结合半监督学习,设计了基于半监督的主动学习图像检索框架。在相关反馈过程中,首先利用半监督学习算法TSVM对标记样本进行训练,然后根据提出的主动学习算法从未标记图像中选取k幅有利于优化学习过程的图像并反馈给用户标记。与传统的相关反馈算法相比,该文提出的图像检索框架显著提高了学习器的效率和性能,并快速收敛于用户的查询概念。     

面向类别不平衡数据的主动在线加权极限学习机算法

针对在样本类别分布不平衡场景下,现有的主动学习算法普遍失效及训练时间过长等问题,提出采用建模速度更快的极限学习机,即ELM(Extreme Learning Machine)作为主动学习的基分类器,并以加权ELM算法用于主动学习过程的平衡控制,进而在理论上推导了其在线学习的过程,大幅降低了主动学习的时间开销,并将最终的混合算法命名为AOW-ELM算法。通过12个基准的二类不平衡数据集验证了该算法的有效性与可行性。     

Multiple-view multiple-learner active learning

Generally, collecting a large quantity of unlabeled examples is feasible, but labeling them all is not. Active learning can reduce the number of labeled examples needed to train a good classifier. Existing active learning algorithms can be roughly divided into three categories: single-view single-learner (SVSL) active learning, multiple-view single-learner (MVSL) active learning and single-view multiple-learner (SVML) active learning. In this paper, a new approach that incorporates multiple views and multiple learners (MVML) into active learning is proposed. Multiple artificial neural networks are used as learners in each view, and they are set with different numbers of hidden neurons and weights to ensure each of them has a different bias. The selective sampling of our proposed method is implemented in three different ways. For comparative purpose, the traditional methods MVSL and SVML active learning as well as bagging active learning and adaboost active learning are also implemented together with MVML active learning in our experiments. The empirical results indicate that the MVML active learning outperforms the other traditional methods.     

基于采样策略的主动学习算法研究进展

主动学习算法通过选择信息含量大的未标记样例交由专家进行标记,多次循环使分类器的正确率逐步提高,进而在标记总代价最小的情况下获得分类器的强泛化能力,这一技术引起了国内外研究人员的关注.侧重从采样策略的角度,详细介绍了主动学习中学习引擎和采样引擎的工作过程,总结了主动学习算法的理论研究成果,详细评述了主动学习的研究现状和发展动态.首先,针对采样策略选择样例的不同方式将主动学习算法划分为不同类型,进而,对基于不同采样策略的主动学习算法进行了深入地分析和比较,讨论了各种算法适用的应用领域及其优缺点.最后指出了存在的开放性问题和进一步的研究方向.     

An analysis of collaborative problem‐solving activities mediated by individual‐based and collaborative computer simulations

Researchers have indicated that the collaborative problem‐solving space afforded by the collaborative systems significantly impact the problem‐solving process. However, recent investigations into collaborative simulations, which allow a group of students to jointly manipulate a problem in a shared problem space, have yielded divergent results regarding their effects on collaborative learning. Hence, this study analysed how students solved a physics problem using individual‐based and collaborative simulations to understand their effects on science learning. Multiple data sources including group discourse, problem‐solving activities, learning test scores, and questionnaire feedback were analysed. Lag sequential analysis on the data found that students using the two simulations collaborated with peers to solve the problem in significantly different patterns. The students using the collaborative simulations demonstrated active engagement in the collaborative activity; however, they did not transform discussions into workable problem‐solving activities. The students using the individual‐based simulation showed a lower level of collaboration engagement, starting with individual exploration of the problem with the simulation, followed by group reflection. The two groups also showed significant differences in their learning test scores. The findings and pedagogical suggestions are discussed in the hope of addressing critical activity design issues in using computer simulations for facilitating collaborative learning.     

Batch Mode Active Learning with Applications to Text Categorization and Image Retrieval

Most machine learning tasks in data classification and information retrieval require manually labeled data examples in the training stage. The goal of active learning is to select the most informative examples for manual labeling in these learning tasks. Most of the previous studies in active learning have focused on selecting a single unlabeled example in each iteration. This could be inefficient, since the classification model has to be retrained for every acquired labeled example. It is also inappropriate for the setup of information retrieval tasks where the user's relevance feedback is often provided for the top K retrieved items. In this paper, we present a framework for batch mode active learning, which selects a number of informative examples for manual labeling in each iteration. The key feature of batch mode active learning is to reduce the redundancy among the selected examples such that each example provides unique information for model updating. To this end, we employ the Fisher information matrix as the measurement of model uncertainty, and choose the set of unlabeled examples that can efficiently reduce the Fisher information of the classification model. We apply our batch mode active learning framework to both text categorization and image retrieval. Promising results show that our algorithms are significantly more effective than the active learning approaches that select unlabeled examples based only on their informativeness for the classification model.     

主动贝叶斯网络分类器

在机器学习中，主动学习具有很长的研究历史。给出了主动贝叶斯分类模型，并讨论了主动学习中几种常用的抽样策略。提出了基于最大最小熵的主动学习方法和基于不确定抽样与最小分类损失相结合的主动学习策略，给出了增量地分类测试实例和修正分类参数的方法。人工和实际的数据实验结果表明，提出的主动学习方法在少量带有类别标注训练样本的情况下获得了较好的分类精度和召回率。     

一种动态的主动多分类方法

在面向大数据问题的应用领域中,由于现实世界的多样性和复杂性,经常会遇到大规模的多类别数据挖掘问题,传统的多分类方法一方面存在着超平面不平衡更新的问题,另一方面学习效率较低,对于复杂的多类别数据无法进行高效分类。针对这个问题,本文提出了一种改进的动态主动多分类（Dynamical active multiple classification, DYA）方法,该方法通过将死锁、激活等概念引入到主动多分类过程,在主动多分类过程中随着分类器的不断更新,动态地控制样本是否参与主动学习的过程;同时,采用分位计数、轮换学习方式的主动多分类方法,使得多类别的分类器能够得到平衡的学习和更新。实验结果表明,本文提出的动态主动多分类方法有效提高了模型的学习效率和泛化性能。     

Supporting executive functions during children's preliteracy learning with the computer

The present study examined how embedded activities to support executive functions helped children to benefit from a computer intervention that targeted preliteracy skills. Three intervention groups were compared on their preliteracy gains in a randomized controlled trial design: an experimental group that worked with software to stimulate early literacy with embedded executive‐functioning support (EL + EF group), an experimental group that worked with the same early literacy software without the explicit EF‐support (EL group) and a control group that played with language discovery games from the same software. These groups were contrasted on their preliteracy progress over time and on their learning behaviours while working with the software. Results showed that children in the two experimental groups progressed more in preliteracy skills on the long‐term, with the EL + EF group showing the highest learning effects. These results were mainly shown for the children with lower levels of EFs. Moreover, children in the EL + EF group showed more independent behaviour and played more games than children in the EL group. These results indicate that young children can show more effective learning over time during computer interventions when their executive functions are kept active.     

一种新的SVM主动学习算法及其在障碍物检测中的应用

障碍物检测是智能机器人要解决的非结构复杂环境感知的典型问题之一.在实际情况中,获得大量未标记样本是相对容易的,而标记这些样本则是极其繁琐和费时的工作,当前的研究工作很少涉及到这类问题的解决办法.将SVM主动学习算法引入到障碍物检测中,针对常规的SVM主动学习算法在应用中所遇到的问题和局限性,采用一种动态聚类过程来选取最有代表性样本和根据专家标记与当前SVM分类结果的差值来调整SVM超平面位置的两种策略对其进行了改进,提出了一种新的主动学习算法--KSVMactiv算法,并在真实的野外环境图像库上进行了实验.由实验结果可知:KSVMactiv算法仅用81个样本就能达到很高的检测效果,从而说明它能显著减少数据标记的工作量,且与已有主动学习算法相比收敛速度更快.     

基于深度贝叶斯主动学习的高光谱图像分类

针对高光谱图像分类中标记样本获取费时费力,无标记数据难以得到有效利用以及主动学习与深度学习结合难等问题,结合贝叶斯深度学习与主动学习的最新进展,提出一种基于深度贝叶斯的主动学习高光谱图像分类算法。利用少量标记样本训练一个卷积神经网络模型,根据与贝叶斯方法结合的主动学习采样策略从无标记样本中选择模型分类最不确定性的样本,选取的样本经人工标记后加入到训练集重新训练模型,减小模型不确定性,提高模型分类精度。通过PaviaU高光谱图像分类的实验结果表明,在少量的标记样本下,提出的方法比传统的方法分类效果更好。     

Variational Bayes for continuous hidden Markov models and its application to active learning

In this paper, we present a variational Bayes (VB) framework for learning continuous hidden Markov models (CHMMs), and we examine the VB framework within active learning. Unlike a maximum likelihood or maximum a posteriori training procedure, which yield a point estimate of the CHMM parameters, VB-based training yields an estimate of the full posterior of the model parameters. This is particularly important for small training sets since it gives a measure of confidence in the accuracy of the learned model. This is utilized within the context of active learning, for which we acquire labels for those feature vectors for which knowledge of the associated label would be most informative for reducing model-parameter uncertainty. Three active learning algorithms are considered in this paper: 1) query by committee (QBC), with the goal of selecting data for labeling that minimize the classification variance, 2) a maximum expected information gain method that seeks to label data with the goal of reducing the entropy of the model parameters, and 3) an error-reduction-based procedure that attempts to minimize classification error over the test data. The experimental results are presented for synthetic and measured data. We demonstrate that all of these active learning methods can significantly reduce the amount of required labeling, compared to random selection of samples for labeling.     

Active learning for on-road vehicle detection: a comparative study

In recent years, active learning has emerged as a powerful tool in building robust systems for object detection using computer vision. Indeed, active learning approaches to on-road vehicle detection have achieved impressive results. While active learning approaches for object detection have been explored and presented in the literature, few studies have been performed to comparatively assess costs and merits. In this study, we provide a cost-sensitive analysis of three popular active learning methods for on-road vehicle detection. The generality of active learning findings is demonstrated via learning experiments performed with detectors based on histogram of oriented gradient features and SVM classification (HOG–SVM), and Haar-like features and Adaboost classification (Haar–Adaboost). Experimental evaluation has been performed on static images and real-world on-road vehicle datasets. Learning approaches are assessed in terms of the time spent annotating, data required, recall, and precision.     

Learning from labeled and unlabeled data using a minimal number of queries

The considerable time and expense required for labeling data has prompted the development of algorithms which maximize the classification accuracy for a given amount of labeling effort. On the one hand, the effort has been to develop the so-called "active learning" algorithms which sequentially choose the patterns to be explicitly labeled so as to realize the maximum information gain from each labeling. On the other hand, the effort has been to develop algorithms that can learn from labeled as well as the more abundant unlabeled data. Proposed in this paper is an algorithm that integrates the benefits of active learning with the benefits of learning from labeled and unlabeled data. Our approach is based on reversing the roles of the labeled and unlabeled data. Specifically, we use a Genetic Algorithm (GA) to iteratively refine the class membership of the unlabeled patterns so that the maximum a posteriori (MAP) based predicted labels of the patterns in the labeled dataset are in agreement with the known labels. This reversal of the role of labeled and unlabeled patterns leads to an implicit class assignment of the unlabeled patterns. For active learning, we use a subset of the GA population to construct multiple MAP classifiers. Points in the input space where there is maximal disagreement amongst these classifiers are then selected for explicit labeling. The learning from labeled and unlabeled data and active learning phases are interlaced and together provide accurate classification while minimizing the labeling effort.     

自适应主动半监督学习方法

主动学习从大量无标记样本中挑选样本交给专家标记.现有的批抽样主动学习算法主要受3个限制：（1）一些主动学习方法基于单选择准则或对数据、模型设定假设,这类方法很难找到既有不确定性又有代表性的未标记样本;（2）现有批抽样主动学习方法的性能很大程度上依赖于样本之间相似性度量的准确性,例如预定义函数或差异性衡量;（3）噪声标签问题一直影响批抽样主动学习算法的性能.提出一种基于深度学习批抽样的主动学习方法.通过深度神经网络生成标记和未标记样本的学习表示和采用标签循环模式,使得标记样本与未标记样本建立联系,再回到相同标签的标记样本.这样同时考虑了样本的不确定性和代表性,并且算法对噪声标签具有鲁棒性.在提出的批抽样主动学习方法中,算法使用的子模块函数确保选择的样本集合具有多样性.此外,自适应参数的优化,使得主动学习算法可以自动平衡样本的不确定性和代表性.将提出的主动学习方法应用到半监督分类和半监督聚类中,实验结果表明,所提出的主动学习方法的性能优于现有的一些先进的方法.     

Active Sampling for Class Probability Estimation and Ranking

In many cost-sensitive environments class probability estimates are used by decision makers to evaluate the expected utility from a set of alternatives. Supervised learning can be used to build class probability estimates; however, it often is very costly to obtain training data with class labels. Active learning acquires data incrementally, at each phase identifying especially useful additional data for labeling, and can be used to economize on examples needed for learning. We outline the critical features of an active learner and present a sampling-based active learning method for estimating class probabilities and class-based rankings. BOOTSTRAP-LV identifies particularly informative new data for learning based on the variance in probability estimates, and uses weighted sampling to account for a potential example's informative value for the rest of the input space. We show empirically that the method reduces the number of data items that must be obtained and labeled, across a wide variety of domains. We investigate the contribution of the components of the algorithm and show that each provides valuable information to help identify informative examples. We also compare BOOTSTRAP-LV with UNCERTAINTY SAMPLING, an existing active learning method designed to maximize classification accuracy. The results show that BOOTSTRAP-LV uses fewer examples to exhibit a certain estimation accuracy and provide insights to the behavior of the algorithms. Finally, we experiment with another new active sampling algorithm drawing from both UNCERTAINTY SAMPLING and BOOTSTRAP-LV and show that it is significantly more competitive with BOOTSTRAP-LV compared to UNCERTAINTY SAMPLING. The analysis suggests more general implications for improving existing active sampling algorithms for classification.