融合极端学习机的判别性分析字典学习算法

研究表明,端学习机和判别性字典学习算法在图像分类领域极具有高效和准确的优势。然而,这两种方法也具有各自的缺点,极端学习机对噪声的鲁棒性较差,判别性字典学习算法在分类过程中耗时较长。为统一这种互补性以提高分类性能,文中提出了一种融合极端学习机的判别性分析字典学习模型。该模型利用迭代优化算法学习最优的判别性分析字典和极端学习机分类器。为验证所提算法的有效性,利用人脸数据集进行分类。实验结果表明,与目前较为流行的字典学习算法和极端学习机相比,所提算法在分类过程中具有更好的效果。     

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.     

Flexible latent variable models for multi-task learning

Given multiple prediction problems such as regression or classification, we are interested in a joint inference framework that can effectively share information between tasks to improve the prediction accuracy, especially when the number of training examples per problem is small. In this paper we propose a probabilistic framework which can support a set of latent variable models for different multi-task learning scenarios. We show that the framework is a generalization of standard learning methods for single prediction problems and it can effectively model the shared structure among different prediction tasks. Furthermore, we present efficient algorithms for the empirical Bayes method as well as point estimation. Our experiments on both simulated datasets and real world classification datasets show the effectiveness of the proposed models in two evaluation settings: a standard multi-task learning setting and a transfer learning setting.     

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.     

基于信息传播节点集的CTDN节点分类算法

针对连续时间动态网络的节点分类问题,根据实际网络信息传播特点定义信息传播节点集,改进网络表示学习的节点序列采样策略,并设计基于信息传播节点集的连续时间动态网络节点分类算法,通过网络表示学习方法生成的节点低维向量以及OpenNE框架内的LogicRegression分类器,获得连续时间动态网络的节点分类结果。实验结果表明,与CTDNE和STWalk算法相比,该算法在实验条件相同的情况下,网络表示学习结果的二维可视化效果更优且最终的网络节点分类精度更高。     

Transfer active learning by querying committee简

In real applications of inductive learning for classifi cation, labeled instances are often defi cient, and labeling them by an oracle is often expensive and time-consuming. Active learning on a single task aims to select only informative unlabeled instances for querying to improve the classifi cation accuracy while decreasing the querying cost. However, an inevitable problem in active learning is that the informative measures for selecting queries are commonly based on the initial hypotheses sampled from only a few labeled instances. In such a circumstance, the initial hypotheses are not reliable and may deviate from the true distribution underlying the target task. Consequently, the informative measures will possibly select irrelevant instances. A promising way to compensate this problem is to borrow useful knowledge from other sources with abundant labeled information, which is called transfer learning. However, a signifi cant challenge in transfer learning is how to measure the similarity between the source and the target tasks. One needs to be aware of different distributions or label assignments from unrelated source tasks;otherwise, they will lead to degenerated performance while transferring. Also, how to design an effective strategy to avoid selecting irrelevant samples to query is still an open question. To tackle these issues, we propose a hybrid algorithm for active learning with the help of transfer learning by adopting a divergence measure to alleviate the negative transfer caused by distribution differences. To avoid querying irrelevant instances, we also present an adaptive strategy which could eliminate unnecessary instances in the input space and models in the model space. Extensive experiments on both the synthetic and the real data sets show that the proposed algorithm is able to query fewer instances with a higher accuracy and that it converges faster than the state-of-the-art methods.     

Moment Kernels for Regular Distributions

Many machine learning problems in natural language processing, transaction-log analysis, or computational biology, require the analysis of variable-length sequences, or, more generally, distributions of variable-length sequences.Kernel methods introduced for fixed-size vectors have proven very successful in a variety of machine learning tasks. We recently introduced a new and general kernel framework, rational kernels, to extend these methods to the analysis of variable-length sequences or more generally distributions given by weighted automata. These kernels are efficient to compute and have been successfully used in applications such as spoken-dialog classification with Support Vector Machines.However, the rational kernels previously introduced in these applications do not fully encompass distributions over alternate sequences. They are based only on the counts of co-occurring subsequences averaged over the alternate paths without taking into accounts information about the higher-order moments of the distributions of these counts.In this paper, we introduce a new family of rational kernels, moment kernels, that precisely exploits this additional information. These kernels are distribution kernels based on moments of counts of strings. We describe efficient algorithms to compute moment kernels and apply them to several difficult spoken-dialog classification tasks. Our experiments show that using the second moment of the counts of n-gram sequences consistently improves the classification accuracy in these tasks.Editors: Dan Roth and Pascale Fung     

Improving the accuracy of decision tree induction by feature preselection

Selecting the right set of features for classification is one of the most important problems in designing a good classifier. Decision tree induction algorithms such as C4.5 have incorporated in their learning phase an automatic feature selection strategy, while some other statistical classification algorithms require the feature subset to be selected in a preprocessing phase. It is well known that correlated and irrelevant features may degrade the performance of the C4.5 algorithm. In our study, we evaluated the influence of feature preselection on the prediction accuracy of C4.5 using a real-world data set. We observed that accuracy of the C4.5 classifier could be improved with an appropriate feature preselection phase for the learning algorithm. Beyond that, the number of features used for classification can be reduced, which is important for image interpretation tasks since feature calculation is a time-consuming process.     

Instance-Based Learning Algorithms

Storing and using specific instances improves the performance of several supervised learning algorithms. These include algorithms that learn decision trees, classification rules, and distributed networks. However, no investigation has analyzed algorithms that use only specific instances to solve incremental learning tasks. In this paper, we describe a framework and methodology, called instance-based learning, that generates classification predictions using only specific instances. Instance-based learning algorithms do not maintain a set of abstractions derived from specific instances. This approach extends the nearest neighbor algorithm, which has large storage requirements. We describe how storage requirements can be significantly reduced with, at most, minor sacrifices in learning rate and classification accuracy. While the storage-reducing algorithm performs well on several real-world databases, its performance degrades rapidly with the level of attribute noise in training instances. Therefore, we extended it with a significance test to distinguish noisy instances. This extended algorithm's performance degrades gracefully with increasing noise levels and compares favorably with a noise-tolerant decision tree algorithm.     

非平稳数据流下的持续学习灾难性遗忘问题求解策略综述

持续学习作为一种在非平稳数据流中不断学习新任务并能保持旧任务性能的特殊机器学习范例,是视觉计算、自主机器人等领域的研究热点,但现阶段灾难性遗忘问题仍然是持续学习的一个巨大挑战。围绕持续学习灾难性遗忘问题展开综述研究,分析了灾难性遗忘问题缓解机理,并从模型参数、训练数据和网络架构三个层面探讨了灾难性遗忘问题求解策略,包括正则化策略、重放策略、动态架构策略和联合策略;根据现有文献凝练了灾难性遗忘方法的评估指标,并对比了不同灾难性遗忘问题的求解策略性能。最后对持续学习相关研究指出了未来的研究方向,以期为研究持续学习灾难性遗忘问题提供借鉴和参考。     

Visual Analytics on Network Forgetting for Task-Incremental Learning

Task-incremental learning (Task-IL) aims to enable an intelligent agent to continuously accumulate knowledge from new learning tasks without catastrophically forgetting what it has learned in the past. It has drawn increasing attention in recent years, with many algorithms being proposed to mitigate neural network forgetting. However, none of the existing strategies is able to completely eliminate the issues. Moreover, explaining and fully understanding what knowledge and how it is being forgotten during the incremental learning process still remains under-explored. In this paper, we propose KnowledgeDrift, a visual analytics framework, to interpret the network forgetting with three objectives: (1) to identify when the network fails to memorize the past knowledge, (2) to visualize what information has been forgotten, and (3) to diagnose how knowledge attained in the new model interferes with the one learned in the past. Our analytical framework first identifies the occurrence of forgetting by tracking the task performance under the incremental learning process and then provides in-depth inspections of drifted information via various levels of data granularity. KnowledgeDrift allows analysts and model developers to enhance their understanding of network forgetting and compare the performance of different incremental learning algorithms. Three case studies are conducted in the paper to further provide insights and guidance for users to effectively diagnose catastrophic forgetting over time.     

面向图像分类的深度模型可解释性研究综述

深度学习目前在计算机视觉、自然语言处理、语音识别等领域得到了深入发展,与传统的机器学习算法相比,深度模型在许多任务上具有较高的准确率.然而,作为端到端的具有高度非线性的复杂模型,深度模型的可解释性没有传统机器学习算法好,这为深度学习在现实生活中的应用带来了一定的阻碍.深度模型的可解释性研究具有重大意义而且是非常必要的,近年来许多学者围绕这一问题提出了不同的算法.针对图像分类任务,将可解释性算法分为全局可解释性和局部可解释性算法.在解释的粒度上,进一步将全局解释性算法分为模型级和神经元级的可解释性算法,将局部可解释性算法划分为像素级特征、概念级特征以及图像级特征可解释性算法.基于上述分类框架,总结了常见的深度模型可解释性算法以及相关的评价指标,同时讨论了可解释性研究面临的挑战和未来的研究方向.认为深度模型的可解释性研究和理论基础研究是打开深度模型黑箱的必要途径,同时可解释性算法存在巨大潜力可以为解决深度模型的公平性、泛化性等其他问题提供帮助.     

On the Convergence of Temporal-Difference Learning with Linear Function Approximation

The asymptotic properties of temporal-difference learning algorithms with linear function approximation are analyzed in this paper. The analysis is carried out in the context of the approximation of a discounted cost-to-go function associated with an uncontrolled Markov chain with an uncountable finite-dimensional state-space. Under mild conditions, the almost sure convergence of temporal-difference learning algorithms with linear function approximation is established and an upper bound for their asymptotic approximation error is determined. The obtained results are a generalization and extension of the existing results related to the asymptotic behavior of temporal-difference learning. Moreover, they cover cases to which the existing results cannot be applied, while the adopted assumptions seem to be the weakest possible under which the almost sure convergence of temporal-difference learning algorithms is still possible to be demonstrated.     

元迁移学习在少样本跨域图像分类中的研究

目的 现有基于元学习的主流少样本学习方法假设训练任务和测试任务服从相同或相似的分布,然而在分布差异较大的跨域任务上,这些方法面临泛化能力弱、分类精度差等挑战。同时,基于迁移学习的少样本学习方法没有考虑到训练和测试阶段样本类别不一致的情况,在训练阶段未能留下足够的特征嵌入空间。为了提升模型在有限标注样本困境下的跨域图像分类能力,提出简洁的元迁移学习（compressed meta transfer learning,CMTL）方法。方法 基于元学习,对目标域中的支持集使用数据增强策略,构建新的辅助任务微调元训练参数,促使分类模型更加适用于域差异较大的目标任务。基于迁移学习,使用自压缩损失函数训练分类模型,以压缩源域中基类数据所占据的特征嵌入空间,微调阶段引导与源域分布差异较大的新类数据有更合适的特征表示。最后,将以上两种策略的分类预测融合视为最终的分类结果。结果 使用mini-ImageNet作为源域数据集进行训练,分别在EuroSAT(EuropeanSatellite)、ISIC(InternationalSkinImagingCollaboration)、CropDiseas(Cr...     

基于最优子段深度学习的手指运动想象脑电信号分类研究

目前已有的手指运动想象脑电信号多分类任务的分类性能均难以达到可用性能。在详细分析脑电信号时间尺度上的多种成分的基础上,设计一种信号子段提取的自监督子网络,然后把子段输入下一个子网络用于信号分类,两个子网综合成一个自监督混合的多任务深度网络。在训练阶段,子段提取子网络针对每条脑电信号提取不同的子段,由后面的分类子网络来判断该子段是否最佳而自动调整子段位置,总体损失函数由两个子网络的两个损失函数加权而成,通过整体网络学习算法实现最佳子段信号的提取并获得最佳分类效果。验证和测试阶段,子段提取子网络按照训练完成的参数自动提取相应的子段输入分类子网络进行分类。在the largest SCP data of Motor-Imagery和BCI Competition IV中Data sets 4数据集上进行网络性能验证,SCP数据集上全部受试者3指分类任务的平均测试分类准确率达70%以上,4指平均测试分类准确率达60%左右,5指平均测试分类准确率达50%左右,比现有的报道有明显的提升。证实该网络能够有效地提取出运动想象脑电信号子段,具有良好的分类效果和泛化性能。     

Forgetting Exceptions is Harmful in Language Learning

We show that in language learning, contrary to received wisdom, keeping exceptional training instances in memory can be beneficial for generalization accuracy. We investigate this phenomenon empirically on a selection of benchmark natural language processing tasks: grapheme-to-phoneme conversion, part-of-speech tagging, prepositional-phrase attachment, and base noun phrase chunking. In a first series of experiments we combine memory-based learning with training set editing techniques, in which instances are edited based on their typicality and class prediction strength. Results show that editing exceptional instances (with low typicality or low class prediction strength) tends to harm generalization accuracy. In a second series of experiments we compare memory-based learning and decision-tree learning methods on the same selection of tasks, and find that decision-tree learning often performs worse than memory-based learning. Moreover, the decrease in performance can be linked to the degree of abstraction from exceptions (i.e., pruning or eagerness). We provide explanations for both results in terms of the properties of the natural language processing tasks and the learning algorithms.     

三维点云配准方法研究进展

点云是一种3维表示方式,在广泛应用的同时产生了对点云处理的诸多挑战。其中,点云配准是一项非常值得研究的工作。点云配准旨在将多个点云正确配准到同一个坐标系下,形成更完整的点云。点云配准要应对点云非结构化、不均匀和噪声等干扰,要以更短的时间消耗达到更高的精度,时间消耗和精度往往是矛盾的,但在一定程度上优化是有可能的。点云配准广泛应用于3维重建、参数评估、定位和姿态估计等领域,在自动驾驶、机器人和增强现实等新兴应用上也有点云配准技术的参与。为此,研究者开发了多样巧妙的点云配准方法。本文梳理了一些比较有代表性的点云配准方法并进行分类总结,对比相关工作,尽量覆盖点云配准的各种形式,并对一些方法的细节加以分析介绍。将现有方法归纳为非学习方法和基于学习的方法进行分析。非学习方法分为经典方法和基于特征的方法;基于学习的方法分为结合了非学习方法的部分学习方法和直接的端到端学习方法。本文分别介绍了各类方法的典型算法,并对比总结算法特性,展望了点云配准技术的未来研究方向。     

多层校正的无监督领域自适应方法

目的 目前深度神经网络已成功应用于众多机器学习任务,并展现出惊人的性能提升效果。然而传统的深度网络和机器学习算法都假定训练数据和测试数据服从的是同一分布,而这种假设在实际应用中往往是不成立的。如果训练数据和测试数据的分布差异很大,那么由传统机器学习算法训练出来的分类器的性能将会大大降低。为了解决此类问题,提出了一种基于多层校正的无监督领域自适应方法。方法 首先利用多层校正来调整现有的深度网络,利用加法叠加来完美对齐源域和目标域的数据表示;然后采用多层权值最大均值差异来适应目标域,增加网络的表示能力;最后提取学习获得的域不变特征来进行分类,得到目标图像的识别效果。结果 本文算法在Office-31图像数据集等4个数字数据集上分别进行了测试实验,以对比不同算法在图像识别和分类方面的性能差异,并进行准确度测量。测试结果显示,与同领域算法相比,本文算法在准确率上至少提高了5%,在应对照明变化、复杂背景和图像质量不佳等干扰情况时,亦能获得较好的分类效果,体现出更强的鲁棒性。结论 在领域自适应相关数据集上的实验结果表明,本文方法具备一定的泛化能力,可以实现较高的分类性能,并且优于其他现有的无监督领域自适应方法。     

文本分类的归纳学习算法和描述

文本分类将自然语言文本接内容归入一个或多个预定义类别中，在许多信息组织和管理中都是一项重要的内容。不同算法的分类准确性各不相同。通过训练实例可以得到准确率很高的文本分类器。     

Classification and recognition of dynamical models: the role of phase, independent components, kernels and optimal transport

We address the problem of performing decision tasks, and in particular classification and recognition, in the space of dynamical models in order to compare time series of data. Motivated by the application of recognition of human motion in image sequences, we consider a class of models that include linear dynamics, both stable and marginally stable (periodic), both minimum and non-minimum phase, driven by non-Gaussian processes. This requires extending existing learning and system identification algorithms to handle periodic modes and nonminimum phase behavior, while taking into account higher-order statistics of the data. Once a model is identified, we define a kernel-based cord distance between models that includes their dynamics, their initial conditions as well as input distribution. This is made possible by a novel kernel defined between two arbitrary (non-Gaussian) distributions, which is computed by efficiently solving an optimal transport problem. We validate our choice of models, inference algorithm, and distance on the tasks of human motion synthesis (sample paths of the learned models), and recognition (nearest-neighbor classification in the computed distance). However, our work can be applied more broadly where one needs to compare historical data while taking into account periodic trends, non-minimum phase behavior, and non-Gaussian input distributions.