您现在的位置:首页>外文期刊>Neurocomputing

期刊信息

  • 期刊名称:

    Neurocomputing

  • 中文名称: 神经计算
  • 刊频: 1.440
  • ISSN: 0925-2312
  • 出版社: -
  • 简介:
  • 排序:
  • 显示:
  • 每页:
全选(0
<1/20>
12338条结果
  • 机译 混合视图网络及其在多视图医学成像中的应用
    摘要: This paper examines data fusion methods for multi-view data classification. We present a decision concept that explicitly takes into account the input multi-view structure, where for each case there is a different subset of relevant views. This data fusion concept, which we dub Mixture of Views, is implemented by a special purpose neural network architecture. The single view decisions are combined by a data-driven decision, into a global decision according to the relevance of each view in a given case. The method was applied to two challenging computer-aided diagnosis (CADx) tasks: the task of classifying breast microcalcifications as benign or malignant based on craniocaudal (CC) and mediolateral oblique (MLO) mammography views and segmenting Multiple Sclerosis (MS) white matter lesions. The experimental results show that our method outperforms previously suggested fusion methods. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 二次网络的模糊逻辑解释
    摘要: Over past several years, deep learning has achieved huge successes in various applications. However, such a data-driven approach is often criticized for lack of interpretability. Recently, we proposed artificial quadratic neural networks consisting of quadratic neurons in potentially many layers. In cellular level, a quadratic function is used to replace the inner product in a traditional neuron, and then undergoes a nonlinear activation. With a single quadratic neuron, any fuzzy logic operation, such as XOR, can be implemented. In this sense, any deep network constructed with quadratic neurons can be interpreted as a deep fuzzy logic system. Since traditional neural networks and quadratic counterparts can represent each other and fuzzy logic operations are naturally implemented in quadratic neural networks, it is plausible to explain how a deep neural network works with a quadratic network as the system model. In this paper, we generalize and categorize fuzzy logic operations implementable with individual quadratic neurons, and then perform statistical/information-theoretic analyses of exemplary quadratic neural networks. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 使用递归神经条件随机场的否定和推测范围检测
    摘要: Negation and speculation scope detection is an important task in natural language processing. Previous studies all show that syntactic information is crucial to the task. However, these work mainly focuses on human-designed discrete features and local features extracted from dependency tree, limiting the performance of the task. In this paper, we propose a recursive neural network sequence labeling model, representing whole dependency tree globally and learning automatically syntactic features, for the task. Specifically, recursive neural network first learns a high-level representation for the words in the context of each sentence, and captures the cue word with its target scope through the global dependency structure. Then, CRFs layer takes the representation from recursive neural network as input to jointly decode labels for the whole sentence. Experimental results on English dataset BioScope and Chinese dataset CNeSp show that our model outperforms the state-of-the-art systems. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 使用签名的合成合成和Siamese神经网络进行离线手写签名验证
    摘要: In this work, we propose the use of Siamese Neural Networks to help solve the off-line handwritten signature verification problem with random forgeries in a writer-independent context. Our proposed solution can be used on new signers without the need for any additional training. Also, we have analyzed three types of synthetic data to increase the amount of samples and the variability needed for training deep neural networks: augmented data samples from GAVAB dataset, a proposal of compositional synthetic signature generation from shape primitives and the GPDSSynthetic dataset. The first two approaches are "on-demand" generators and they can be used during the training stage to produce a potentially infinite number of synthetic signatures. In our approach, we initially trained Siamese Neural Networks using signatures from GAVAB dataset and different combinations of synthetic data. The best verification results were obtained when combining original and synthetic signatures for training. Additionally, we tested our approach on the GPSSynthetic, MCYT, SigComp11 and CEDAR datasets demonstrating the generalization capabilities of our proposal. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 异构动态代理的赢家通吃竞争
    摘要: Winner-take-all competition exists widely in nature and has been applied in many engineering fields. This paper mainly investigates a group of heterogeneous dynamic agents, which produce the winner-take-all competition. For the heterogeneous system consisting of first- and second-order dynamic agents, we propose two different kinds of protocols with and without velocity measurements, respectively. Firstly, we employ the Lasalle's invariant principle to solve the equilibrium points of the proposed system. Secondly, we prove that the proposed protocols can solve the winner-take-all problems for the heterogeneous systems. The results reveal that winner is independent from the dynamics of agents, but is determined by inputs. Finally, some examples are also gave to verify the validity of the proposed protocols. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 otsad:用于在线时间序列异常检测器的软件包
    摘要: This paper presents otsad, the first R package which implements a set of novel online detection algorithms for univariate time-series. Moreover, this package also provides advanced functionalities and contents such as new false positive reduction algorithm and the novel NAB detectors measurement technique which is specifically designed to measure online time-series anomaly detectors. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 使用振动干扰的运动检测的神经形态实现
    摘要: Motion detection is paramount for computational vision processing. This is however a particularly challenging task for a neuromorphic hardware in which algorithms are based on interconnected spiking entities, as the instantaneous visual stimuli reports merely on luminance change. Here we describe a neuromorphic algorithm, in which an array of neuro-oscillators is utilized to detect motion and its direction over an entire field of view. These oscillators are induced via phase shifted Gabor functions, allowing them to oscillate in response to motion in one predefined direction, and to dump to zero otherwise. We developed the algorithm using the Neural Engineering Framework (NEF), making it applicable for a variety of neuromorphic hardware. Our algorithm extends the existing growing set of approaches aiming at utilizing neuromorphic hardware for vision processing, which enable to minimize energy exploitation and silicon area while enhancing computational capabilities. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 数据像素化,用于预测事件的完成时间
    摘要: Nowadays, a company uses many sensors to record its entire activity process; the recorded data are called event-log. However, event-log prevalently contains discrete data that many powerful machine-learning algorithms are unable to deal with. One-hot encoding is an outstanding method for transforming discrete data into a binary vector. Nonetheless, if there are many distinct values, the problem of dimensionality will be incurred. To tackle this issue, we propose a new approach, called the Pixelization method, which transforms event data into images. We experimentally performed causal inference for prediction of pixels (representing the processing time of each event) by using a generative model with our novel convolution technique. We compared our approach with a baseline method, one-hot encoding, and an entity-embedded approach combined with a neural network model. The results showed that our approach outperforms the state-of-the-art methods in terms of accuracy. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 混合神经推荐与联合深度表示学习等级和评论
    摘要: Rating-based methods (e.g., collaborative filtering) in recommendation can explicitly model users and items from their rating patterns, nevertheless suffer from the natural data sparsity problem. In other hand, user-generated reviews can provide rich semantic information of user preference and item features, and can alleviate the sparsity problems of rating data. In fact, ratings and reviews are complementary and can be viewed as two different sides of users and items, hence fusing rating patterns and text reviews effectively has the potential to learn more accurate representations of users and items for recommendation. In this paper, we propose a hybrid neural recommendation model to learn the deep representations for users and items from both ratings and reviews. Our model contains three major components, i.e., a rating-based encoder to learn deep and explicit features from rating patterns of users and items, a review-based encoder to model users and items from text reviews, and the prediction module for recommendation according to the rating- and review-based representations of users and items. In addition, considering that different reviews have different informativeness for modelling users and items, we introduce a novel review-level attention mechanism incorporating with rating-based representation as query vector to select useful reviews. We conduct extensive experiments on several benchmark datasets and the experimental results demonstrate that our model can outperform the existing competitive baseline methods in recommendations. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 一种基于解析和显着性检测的补丁重新选择新方法
    摘要: Person re-identification is an important technique towards automatic recognition of a person across non-overlapping cameras. In this paper, a novel patch selection method based on parsing and saliency detection is proposed. The algorithm is divided into two stages. The first stage, primary selection: Deep Decompositional Network (DNN) is adopted to parse a pedestrian image into semantic regions, then sliding window and color matching techniques are proposed to select pedestrian patches and remove background patches. The second stage, secondary selection: saliency detection is utilized to select reliable patches according to saliency map. Finally, PHOG, HSV and SIFT features are extracted from these patches and fused with the global feature LOMO to compensate for the inherent errors of saliency detection. By applying the proposed method on such datasets as VIPeR, PRID2011, CUHK01, CUHK03, PRID 450S and iLIDS-VID, it is found that the proposed descriptor can produce results superior to many state-of-the-art feature representation methods for person identification. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 具有Markovian切换的网络上的随机耦合系统的非周期性间歇控制
    摘要: Throughout this paper, the stabilization problem of random coupled systems on networks with Markovian switching (RCSNMS) is considered via aperiodically intermittent control. It is worth noting that aperiodically intermittent control is firstly utilized to stabilize random systems which are derived by more general noise. On the basis of Lyapunov method, graph theory together with some new stochastic analysis techniques, several stability criteria are derived. Different from most existing stability results on random systems in the literature which are mainly noise-to-state stability, we consider global asymptotical stability in probability and exponential stability in pth moment of RCSNMS. Then an application of the obtained results for a class of random coupled oscillators with Markovian switching via aperiodically intermittent control is presented. Finally, two numerical examples are concerned to demonstrate the validity and feasibility of the theoretical results. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 通过不等式技巧进一步研究延迟惯性神经网络的有限时间同步
    摘要: We discuss the finite-time synchronization of a class of delayed inertial neural networks. Getting rid of utilizing some finite-time synchronization theorems and integral inequality skills used in Zhang et al. (2018), by making good use of new inequality skills, two new concise and easily tested criteria to assure the finite-time synchronization for the discussed delayed master-slave inertial neural networks are acquired. The craftsmanship and results of finite-time synchronization for the master-slave neural networks are different from those in some recent works, consequently, our study on the finite-time synchronization of neural networks has definite significance. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 具有单位超球冠映射和自适应核覆盖的优化概率神经网络
    摘要: It is important to improve the classification accuracy and reduce the storage space when probabilistic neural networks are used for pattern classification tasks. Based on a unit hyperspherical crown mapping and adaptive kernel coverage strategy, this paper presents an optimized hyperspherical crown probabilistic neural network(HCPNN). To overcome the separability problem caused by the fusion of heterogeneous samples, we adopt an unconventional unit hyperspherical crown mapping model in the sample space. Theoretical analysis indicates that nonlinear mapping can improve the separability of the original sample set under certain conditions. In addition, to optimize the pattern layer structure of probabilistic neural networks, we adopt an adaptive kernel coverage method for the training sample space to generate initial pattern nodes. The accumulation potential of the sample in each training subclass is used to measure the distribution density of different classes, and an adaptive update mechanism of potential values is established. In each iteration, nodes with high accumulation potential values are searched as pattern nodes from the dense to sparse regions. The precise position of each pattern node and the corresponding kernel width are adjusted by the Expected Maximum algorithm. Experiments show that HCPNN outperforms other algorithms with respect to the classification performance. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 子空间扩展稀疏表示与判别特征学习的人脸识别方法
    摘要: To address the problem of face recognition where the number of the labeled samples is insufficient and those samples involve pose, illumination and expression variations, etc., this paper proposes a face recognition approach by subspace extended sparse representation and discriminative feature learning, called SESRC & LDF. In SESRC&LDF, each test image is considered to be the image with small pose variation or the image with large pose variation according to its symmetry. For each test image, if it is considered to be the former, it will be recognized by the proposed subspace extended sparse representation classifier (SESRC), otherwise, it will be recognized by the face recognition method based on learning discriminative feature (LDF) proposed in this paper. On eight benchmark face databases, including Yale, AR, LFW, Extended Yale B, FEI, FERET, UMIST and Georgia Tech, empirical results show that SESRC & LDF achieves the highest recognition rates, outperforming many algorithms. Those algorithms include some state-of-the-art ones, such as PLR, MDFR and OPR. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 具有拮抗作用的异构线性多智能体系统的自适应二分输出共识
    摘要: This paper addresses the problem of bipartite output consensus of heterogeneous linear multi-agent systems with antagonistic interactions. The signed graph is directed and structurally balanced. With the assumption that only the leader can access the output of exosystem, two fully distributed adaptive protocols without using the state information of exosystem are designed based on the states and the observers of states, respectively. Numerical simulation demonstrates the effectiveness of the proposed approach. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 何去何从:针对异构社交网络的有效兴趣点推荐框架
    摘要: Point-of-Interest (POI) recommendation is one of the most essential tasks in LBSNs to help users discover new interesting locations, especially when users travel out of town or to unfamiliar areas. Current studies on POI recommendation in LBSNs mainly focus on modeling multiple factors extracted from users' profiles and checking-in records. Data sparsity and incompleteness of user-POI interaction matrix are very common problems in POI recommendation, especially for the out-of-town scenario. Another challenge is that most information in the LBSNs is unreliable due to users' different backgrounds or preferences. Because of the close relationship between users, information from trustable friends on CommunicationBased Social Networks (CBSNs) is more valuable than that in LBSNs, which can give a preferable suggestion instead of trustless reviews in LBSNs. In this study, we propose a latent probabilistic generative model called HI-LDA (Heterogeneous Information based LDA), which can accurately capture users' words on CBSNs by taking into full consideration the information on LBSNs including geographical effect as well as the abundant information including social relationship, users' interactive behaviors and comment content. In particular, the parameters of the HI-LDA model can be inferred by the Gibbs sampling method in an effective fashion. Beyond these proposed techniques, we introduce an POI recommendation framework integrating geographical clustering approach considering the locations and popularity of POIs simultaneously. Extensive experiments were conducted to evaluate the performance of the proposed framework on two real heterogeneous LBSN-CBSN networks. The experimental results demonstrate the superiority of HI-LDA on effective and efficient POI recommendation in both home-town and out-of-town scenarios, when compared with the state-of-the-art baseline approaches. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 具有分数阶的全复数值神经网络的有限时间同步
    摘要: In this paper, without separating complex-valued neural networks into two real-valued systems, the finite-time synchronization is addressed for a class of fully complex-valued neural networks with fractional-order. Firstly, a new fractional-order differential inequality is established to improve some existing results in the real domain. Besides, to avoid the traditional separation method, the sign function of complex numbers is proposed and some properties about it are derived. Under the proposed sign function framework, by designing some novel and effective control schemes, constructing nontrivial Lyapunov functions and developing some new inequality methods in complex domain, several criteria of finite-time synchronization are derived and the settling-time of synchronization is effectively estimated. Finally, the effectiveness of the theoretical results is demonstrated by some numerical examples. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 MSN:用于RGB-D场景识别的模式分离网络
    摘要: RGB-D image based indoor scene recognition is a challenging task due to the complex scene layouts and cluttered objects. Although the depth modality can provide extra geometric information, how to better learn the multi-modal features is still an open problem. Considering this, in this paper we propose the modality separation networks to extract the modal-consistent and modal-specific features simultaneously. The motivations of this work are from two aspects: 1) The first one is to learn what is unique to each modality and what is common between the two modalities explicitly; 2) The second one is to explore the relationship between global/local features and modal-specific/consistent features. To this end, the proposed framework contains two branches of submodules to learn the multi-modal features. One branch is used to extract the individual characteristics of each modality by minimizing the similarity between two modalities. Another branch is to learn the common information between two modalities by maximizing the correlation term. Moreover, with the spatial attention module, our method can visualize the spatial positions where different submodules focus on. We evaluate our method on two public RGB-D scene recognition datasets, and new state-of-the-art results are achieved with the proposed framework. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 双三元组网络用于图像零镜头学习
    摘要: As a cross-modal task, zero-shot learning (ZSL) is generally achieved by aligning the semantic relationships between different modalities. It is a key issue in the alignment to accurately measure the multimodal data distances. Although metric learning has been employed in many image ZSL approaches, few of them make full use of the data information. To address this issue, we propose a novel deep metric learning framework called Dual-Triplet Network (DTNet) for image ZSL. The DTNet first projects the semantic information into the visual space with a mapping network and then employs two triplet networks for learning the visual-semantic mapping. Specifically, one triplet network focuses on negative attribute features, and the other pays special attention to negative visual features, which guarantees the sufficient discovery and utilization of data information. Extensive experiments on three benchmark datasets demonstrate that our proposed DTNet achieves the state-of-the-art results on both traditional and generalized image ZSL tasks. Especially, on the H measurement of generalized image ZSL, DTNet has improvements of 18% on AwA, 1.9% on CUB, and 12.9% on aPY, respectively. (C) 2019 Elsevier B.V. All rights reserved.
  • 机译 具有全局属性的跨尺度融合检测,用于密集字幕
    摘要: As a new task of image understanding, the dense caption model needs to locate and describe a salient region in the image simultaneously. It inevitably divides the dense caption model into two parts, one part for detecting the regions of interest and the other part for generating regional language caption. Previous methods are relatively simple to deal with these two parts, using the feature map on the last convolution layer of RPN network to predict object coordinates, and using LSTM for regional language modeling. However, the structure of RPN is insufficient to deal with a large number of objects in the complex dataset, and LSTM also fails to effectively utilize the global information of images in regional language training, which brings opportunity to improve the performance of dense caption. In this paper, we propose a novel Cross-scale Fusion with Global Attribute model (CSGA) that enables the two parts of the dense caption model to perform normal end-to-end training without mutual interference. Furthermore, our model uses a one-stage object detector with feature map fusion operation across multiple detection scales to improve the quality of object detection part, and combines image features with the global high-level attribute to improve regional language training. We design a variety of model architectures and conducted sufficient experiments. Empirical results on Visual Genome dataset show that our model achieves competitive results with mAP 8.33. (C) 2019 Elsevier B.V. All rights reserved.
  • 联系方式:010-58892860转803 (工作时间) 18141920177 (微信同号)
  • 客服邮箱:kefu@zhangqiaokeyan.com
  • 京公网安备:11010802029741号 ICP备案号:京ICP备15016152号-1 六维联合信息科技(北京)有限公司©版权所有
  • 客服微信
  • 服务号