基于BLSTM的命名实体识别方法

传统的命名实体识别方法直接依靠大量的人工特征和专门的领域知识,解决了监督学习语料不足的问题,但设计人工特征和获取领域知识的代价昂贵。针对该问题,提出一种基于BLSTM(Bidirectional Long Short-Term Memory)的神经网络结构的命名实体识别方法。该方法不再直接依赖于人工特征和领域知识,而是利用基于上下文的词向量和基于字的词向量,前者表达命名实体的上下文信息,后者表达构成命名实体的前缀、后缀和领域信息;同时,利用标注序列中标签之间的相关性对BLSTM的代价函数进行约束,并将领域知识嵌入模型的代价函数中,进一步增强模型的识别能力。实验表明,所提方法的识别效果优于传统方法。     

Meta-learning meets the Internet of Things: Graph prototypical models for sensor-based human activity recognition

With the rapid growth of the Internet of Things (IoT), smart systems and applications are equipped with an increasing number of wearable sensors and mobile devices. These sensors are used not only to collect data but, more importantly, to assist in tracking and analyzing the daily human activities. Sensor-based human activity recognition is a hotspot and starts to employ deep learning approaches to supersede traditional shallow learning that rely on hand-crafted features. Although many successful methods have been proposed, there are three challenges to overcome: (1) deep model’s performance overly depends on the data size; (2) deep model cannot explicitly capture abundant sample distribution characteristics; (3) deep model cannot jointly consider sample features, sample distribution characteristics, and the relationship between the two. To address these issues, we propose a meta-learning-based graph prototypical model with priority attention mechanism for sensor-based human activity recognition. This approach learns not only sample features and sample distribution characteristics via meta-learning-based graph prototypical model, but also the embeddings derived from priority attention mechanism that mines and utilizes relations between sample features and sample distribution characteristics. What is more, the knowledge learned through our approach can be seen as a priori applicable to improve the performance for other general reasoning tasks. Experimental results on fourteen datasets demonstrate that the proposed approach significantly outperforms other state-of-the-art methods. On the other hand, experiments of applying our model to two other tasks show that our model effectively supports other recognition tasks related to human activity and improves performance on the datasets of these tasks.     

面向人体行为识别的深度特征学习方法比较*

针对人体行为识别问题,比较了两种基于智能手机惯性加速度传感器数据的深度特征学习方法。与传统的人工特征提取方法相比,基于深度特征学习方法可以实现端到端训练,网络结构简单直观,避免了繁琐的特征工程,通过深度神经网络模型的学习自动获得特征。本文通过对比深度卷积神经网络、长短期记忆网络两种深度学习方法在公开网站UCI的机器学习知识库的人体行为识别数据集上的识别效果,论证了基于Dropout深度卷积神经网络特征学习方法的有效性。     

Aerial scene classification via an ensemble extreme learning machine classifier based on discriminative hybrid convolutional neural networks features

Identifying a discriminative feature can effectively improve the classification performance of aerial scene classification. Deep convolutional neural networks (DCNN) have been widely used in aerial scene classification for its learning discriminative feature ability. The DCNN feature can be more discriminative by optimizing the training loss function and using transfer learning methods. To enhance the discriminative power of a DCNN feature, the improved loss functions of pretraining models are combined with a softmax loss function and a centre loss function. To further improve performance, in this article, we propose hybrid DCNN features for aerial scene classification. First, we use DCNN models with joint loss functions and transfer learning from pretrained deep DCNN models. Second, the dense DCNN features are extracted, and the discriminative hybrid features are created using linear connection. Finally, an ensemble extreme learning machine (EELM) classifier is adopted for classification due to its general superiority and low computational cost. Experimental results based on the three public benchmark data sets demonstrate that the hybrid features obtained using the proposed approach and classified by the EELM classifier can result in remarkable performance.     

基于深度卷积神经网络的车型识别

传统的基于卷积神经网络的车型识别算法存在识别相似车型的准确率不高,以及在网络训练时只能使用图像的灰度图从而丢失了图像的颜色信息等缺陷。对此,提出一种基于深度卷积神经网络(Deep Convolution Neural Network,DCNN)的提取图像特征的方法,运用深度卷积神经网络对背景较复杂的车型进行网络训练,以达到识别车型的目的。文中采用先进的深度学习框架Caffe,基于AlexNet结构提出了深度卷积神经网络的模型,分别对车型的图像进行训练,并与传统CNN算法进行比较。实验结果显示,DCNN网络模型的准确率达到了96.9%,比其他算法的准确率更高。     

基于深度网络的可学习感受野算法在图像分类中的应用

作为图像检索,图像组织和机器人视觉的基本任务,图像分类在计算机视觉和机器学习中受到了广泛的关注.用于目标识别及图像分类的多种基于深度学习的模型同样引发了该领域内的极大兴趣.本文提出了一种取代尺度不变特征变换(SIFT)和方向梯度直方图(HOG)描述子的算法,即利用深度分层结构,按层级学习有效的图像表示,直接从原始像素点学习特征.该方法分别利用K--奇异值分解(K--SVD)和正交匹配追踪(OMP)进行字典训练和编码.此外,本文采用了同时学习分类器和用于池化的感受野方案.实验结果证明,上述算法在目标(Oxford flowers)和事件(UIUC--sports)图像分类测试集中取得了更好的分类性能.     

A hybrid of deep learning and hand-crafted features based approach for snow cover mapping

Monitoring the extent of snow cover plays a vital role for a better understanding of current and future climatic, ecological, and water cycle conditions. Previously, several traditional machine learning models have been applied for accomplishing this while exploring a variety of feature extraction techniques on various information sources. However, the laborious process of any amount of hand-crafted feature extraction has not helped to obtain high accuracies. Recently, deep learning models have shown that feature extraction can be made automatic and that they can achieve the required high accuracies but at the cost of requiring a large amount of labelled data. Fortunately, despite the absence of such large amounts of labelled data for this task, we can rely on pre-trained models, which accept red-green-blue (RGB) information (or dimensions-reduced spectral data). However, it is always better to include a variety of information sources to solve any problem, especially with the availability of other important information sources like synthetic aperture radar (SAR) imagery and elevation. We propose a hybrid model where the deep learning is assisted by these information sources which have until now been left out. Particularly, our model learns from both the deep learning features (derived from spectral data) and the hand-crafted features (derived from SAR and elevation). Such an approach shows interesting performance-improvement from 96.02% (through deep learning alone) to 98.10% when experiments were conducted for Khiroi village of the Himalayan region in India.     

Multi-modal knowledge graphs representation learning via multi-headed self-attention

Traditional knowledge graphs (KG) representation learning focuses on the link information between entities, and the effectiveness of learning is influenced by the complexity of KGs. Considering a multi-modal knowledge graph (MKG), due to the introduction of considerable other modal information(such as images and texts), the complexity of KGs further increases, which degrades the effectiveness of representation learning. To resolve this solve the problem, this study proposed the multi-modal knowledge graphs representation learning via multi-head self-attention (MKGRL-MS) model, which improved the effectiveness of link prediction by adding rich multi-modal information to the entity. We first generated a single-modal feature vector corresponding to each entity. Then, we used multi-headed self-attention to obtain the attention degree of different modal features of entities in the process of semantic synthesis. In this manner, we learned the multi-modal feature representation of entities. New knowledge representation is the sum of traditional knowledge representation and an entity’s multi-modal feature representation. Simultaneously, we successfully train our model on two existing models and two different datasets and verified its versatility and effectiveness on the link prediction task.     

Leveraging enterprise knowledge graph to infer web events’ influences via self-supervised learning

Knowledge graph (KG) techniques have achieved successful results in many tasks, especially in semantic web and natural language processing domains. In recent years, representation learning on KG has been successfully applied to e-business applications, such as event-driven automatic investment strategies. However, there is still limited research about learning events’ influence on KG for modern quantitative investment. In this paper, we propose a novel event influence learning framework to predict stock market trends, called ST-Trend, leveraging enterprise knowledge graph to represent company correlation relationships, for mining the deep background knowledge of web events, with three self-supervised learning tasks. In particular, we devise two jointly self-supervised tasks to identify the relations between web events and companies. The first task is for generating ground-truth event-company correlation labels based on the enterprise knowledge graph. The second task is used to train how to identify the correlated companies of an event based on the generated correlation labels, with the encoding of web events, company features, and technical sequential data. We then design the prediction network to infer an event’s influence on stock price trends of the identified correlated companies based on the enterprise KG. Finally, we perform extensive experiments on a massive real-life dataset to validate the effectiveness of our proposed framework, and the experimental results demonstrate its superior performance in predicting stock market trends via considering events’ influences with the enterprise knowledge graph.     

迁移学习在医学图像分类中的研究进展

医学影像作为医疗数据的主要载体,在疾病预防、诊断和治疗中发挥着重要作用。医学图像分类是医学影像分析的重要组成部分。如何提高医学图像分类效率是一个持续的研究问题。随着计算机技术进步,医学图像分类方法已经从传统方法转到深度学习,再到目前热门的迁移学习。虽然迁移学习在医学图像分类中得到较广泛应用,但存在不少问题,本文对该领域的迁移学习应用情况进行综述,从中总结经验和发现问题,为未来研究提供线索。1)对基于迁移学习的医学图像分类研究的重要文献进行梳理、分析和总结,概括出3种迁移学习策略,即迁移模型的结构调整策略、参数调整策略和从迁移模型中提取特征的策略;2)从各文献研究设计的迁移学习过程中提炼共性,总结为5种迁移学习模式,即深度卷积神经网络(deep convolution neural network, DCNN)模式、混合模式、特征组合分类模式、多分类器融合模式和二次迁移模式。阐述了迁移学习策略和迁移学习模式之间的关系。这些迁移学习策略和模式有助于从更高的抽象层次展现迁移学习应用于医学图像分类领域的情况;3)阐述这些迁移学习策略和模式在医学图像分类中的具体应用,分析这些策略及模式的优点、局...     

A formalized framework for incorporating expert labels in crowdsourcing environment

Crowdsourcing services have been proven efficient in collecting large amount of labeled data for supervised learning tasks. However, the low cost of crowd workers leads to unreliable labels, a new problem for learning a reliable classifier. Various methods have been proposed to infer the ground truth or learn from crowd data directly though, there is no guarantee that these methods work well for highly biased or noisy crowd labels. Motivated by this limitation of crowd data, in this paper, we propose a novel framewor for improving the performance of crowdsourcing learning tasks by some additional expert labels, that is, we treat each labeler as a personal classifier and combine all labelers’ opinions from a model combination perspective, and summarize the evidence from crowds and experts naturally via a Bayesian classifier in the intermediate feature space formed by personal classifiers. We also introduce active learning to our framework and propose an uncertainty sampling algorithm for actively obtaining expert labels. Experiments show that our method can significantly improve the learning quality as compared with those methods solely using crowd labels.     

基于深度学习的行人重识别研究进展

行人重识别是计算机视觉领域近年来非常热的一个研究课题,可以被视为图像检索的一个子问题,其目标是给定一个监控行人图像检索跨设备下的该行人图像.传统的方法依赖手工特征,不能适应数据量很大的复杂环境.近年来随着深度学习的发展,大量基于深度学习的行人重识别方法被提出.本文先简单介绍了该问题的定义及传统方法的局限,并列举了一些适用于深度学习方法的行人重识别数据集.此外我们详细地总结了一些比较典型的基于深度学习的行人重识别方法,并比较了部分算法在Market1501数据集上的性能表现.最后我们对该问题未来的研究方向做了一个展望.     

深度卷积神经网络降噪模型的技术瓶颈与研究展望

现有的深度卷积神经网络（DCNN）图像降噪模型受其技术路线内在固有特性的制约,降噪性能仍然有待进一步改进。为了推动现有DCNN图像降噪模型技术的发展,需要正视并及时解决制约其进一步完善的瓶颈问题。本文简要概述了传统的基于自然图像非局部自相似性、稀疏性和低秩性这3种先验知识设计的图像降噪算法的技术路线特点和优缺点,从传统图像降噪算法存在的问题中引出基于DCNN构建图像降噪模型的技术优势,并梳理并总结了DCNN降噪模型未来的发展瓶颈,就相应的解决方案（研究方向）进行详细讨论。通过深入分析发现,可以从扩大卷积核的感受野、降低网络参数与训练集之间的依赖关系以及充分利用DCNN网络的建模能力这3个角度入手,突破现有基于数据驱动的DCNN降噪模型的瓶颈制约,把图像降噪算法的研究水平推向新的高度。     

图像分类的深度卷积神经网络模型综述

图像分类是计算机视觉中的一项重要任务,传统的图像分类方法具有一定的局限性。随着人工智能技术的发展,深度学习技术越来越成熟,利用深度卷积神经网络对图像进行分类成为研究热点,图像分类的深度卷积神经网络结构越来越多样,其性能远远好于传统的图像分类方法。本文立足于图像分类的深度卷积神经网络模型结构,根据模型发展和模型优化的历程,将深度卷积神经网络分为经典深度卷积神经网络模型、注意力机制深度卷积神经网络模型、轻量级深度卷积神经网络模型和神经网络架构搜索模型等4类,并对各类深度卷积神经网络模型结构的构造方法和特点进行了全面综述,对各类分类模型的性能进行了对比与分析。虽然深度卷积神经网络模型的结构设计越来越精妙,模型优化的方法越来越强大,图像分类准确率在不断刷新的同时,模型的参数量也在逐渐降低,训练和推理速度不断加快。然而深度卷积神经网络模型仍有一定的局限性,本文给出了存在的问题和未来可能的研究方向,即深度卷积神经网络模型主要以有监督学习方式进行图像分类,受到数据集质量和规模的限制,无监督式学习和半监督学习方式的深度卷积神经网络模型将是未来的重点研究方向之一;深度卷积神经网络模型的速度和资源消耗仍不尽人意,应用于移动式设备具有一定的挑战性;模型的优化方法以及衡量模型优劣的度量方法有待深入研究;人工设计深度卷积神经网络结构耗时耗力,神经架构搜索方法将是未来深度卷积神经网络模型设计的发展方向。     

基于深度学习的铁路图像场景分类优化研究

铁路检测、监测领域产生海量的图像数据,基于图像场景进行分类对图像后续分析、管理具有重要价值.本文提出一种结合深度卷积神经神经网络DCNN （Deep Convolutional Neural Networks）与梯度类激活映射Grad-CAM （Grad Class Activation Mapping）的可视化场景分类模型,DCNN在铁路场景分类图像数据集进行迁移学习,实现特征提取,Grad-CAM根据梯度全局平均计算权重实现对类别的加权热力图及激活分数计算,提升分类模型可解释性.实验中对比了不同的DCNN网络结构对铁路图像场景分类任务性能影响,对场景分类模型实现可视化解释,基于可视化模型提出了通过降低数据集内部偏差提升模型分类能力的优化流程,验证了深度学习技术对于图像场景分类任务的有效性.     

Exploring feature sets for two-phase biomedical named entity recognition using semi-CRFs

This paper represents a two-phase approach based on semi-Markov conditional random fields model (semi-CRFs) and explores novel feature sets for identifying the entities in text into 5 types: protein, DNA, RNA, cell_line and cell_type. Semi-CRFs put the label to a segment not a single word which is more natural than the other machine learning methods such as conditional random fields model (CRFs). Our approach divides the biomedical named entity recognition task into two sub-tasks: term boundary detection and semantic labeling. At the first phase, term boundary detection sub-task detects the boundary of the entities and classifies the entities into one type C. At the second phase, semantic labeling sub-task labels the entities detected at the first phase the correct entity type. We explore novel feature sets at both phases to improve the performance. To make a comparison, experiments conducted both on CRFs and on semi-CRFs models at each phase. Our experiments carried out on JNLPBA 2004 datasets achieve an F-score of 74.64 % based on semi-CRFs without deep domain knowledge and post-processing algorithms, which outperforms most of the state-of-the-art systems.     

基于深度时空Q网络的机器人疏散人群算法

针对目前人群疏散方法中机器人灵活性低、场景适应性有限与疏散效率低的问题,提出一种基于深度强化学习的机器人疏散人群算法。利用人机社会力模型模拟突发事件发生时的人群疏散状态,设计一种卷积神经网络结构提取人群疏散场景中复杂的空间特征,将传统的深度Q网络与长短期记忆网络相结合,解决机器人在学习中无法记忆长期时间信息的问题。实验结果表明,与现有基于人机社会力模型的机器人疏散人群方法相比,该算法能够提高在不同仿真场景中机器人疏散人群的效率,从而验证了算法的有效性。     

An innovative hybrid approach for extracting named entities from unstructured text data

Named entity recognition (NER) is the core part of information extraction that facilitates the automatic detection and classification of entities in natural language text into predefined categories, such as the names of persons, organizations, locations, and so on. The output of the NER task is crucial for many applications, including relation extraction, textual entailment, machine translation, information retrieval, etc. Literature shows that machine learning and deep learning approaches are the most widely used techniques for NER. However, for entity extraction, the abovementioned approaches demand the availability of a domain‐specific annotated data set. Our goal is to develop a hybrid NER system composed of rule‐based deep learning as well as clustering‐based approaches, which facilitates the extraction of generic entities (such as person, location, and organization) out of natural language texts of domains that lack generic named entities labeled domain data sets. The proposed approach takes the advantages of both deep learning and clustering approaches but separately, in combination with a knowledge‐based approach by using a postprocessing module. We evaluated the proposed methodology on court cases (judgments) as a use case since it contains generic named entities of different forms that are poorly or not present in open‐source NER data sets. We also evaluated our hybrid models on two benchmark data sets, namely, Computational Natural Language Learning (CoNLL) 2003 and Open Knowledge Extraction (OKE) 2016. The experimental results obtained from benchmark data sets show that our hybrid models achieved substantially better performance in terms of the F‐score in comparison to other competitive systems.     

试题知识点预测:一种教研知识强化的卷积神经网络模型

在各类在线学习系统中,为了给学生提供优质的学习服务,一个基础性的任务是试题知识点预测,即预测一道试题所考察的知识概念、能力等。在这个任务中,已有方法通常基于人工专家标注或者传统机器学习方法。然而,这些传统方法要么耗时耗力,要么仅关注试题资源的浅层特征,忽略了试题文本和知识点之间的深层语义关联。因此,这两类方法在实际应用中均受到了限制。为此,该文提出一种教研知识强化的卷积神经网络方法进行试题知识点预测。首先,结合教育学经验,定义和抽取试题的浅层特征。然后,利用一个卷积神经网络对试题的深层语义进行理解和表征。然后,考虑到教研先验与试题词句之间的关联,提出一种基于注意力机制的方法能够自动识别和计算不同教研先验对试题的重要性程度。最后,设计了一个融合知识点决策和试题语义约束的模型训练目标。该文在大规模数据上进行了充分的实验。实验结果表明,所提出的方法能够有效地进行试题知识点预测,具有很好的应用价值。     

基于GRU和注意力机制的远程监督关系抽取

随着深度学习的发展,越来越多的深度学习模型被运用到了关系提取的任务中,但是传统的深度学习模型无法解决长距离依赖问题;同时,远程监督将会不可避免地产生错误标签。针对以上两个问题,提出一种基于GRU（gated recurrent unit）和注意力机制的远程监督关系抽取方法,首先通过使用GRU神经网络来提取文本特征,解决长距离依赖问题;接着在实体对上构建句子级的注意力机制,减小噪声句子的权重;最后在真实的数据集上,通过计算准确率、召回率并绘出PR曲线证明该方法与现有的一些方法相比,取得了比较显著的进步。