当前期刊: Neural Networks Go to current issue    加入关注    本刊投稿指南
显示样式:        排序: IF: - GO 导出
我的关注
我的收藏
您暂时未登录!
登录
  • Modality independent adversarial network for generalized zero shot image classification
    Neural Netw. (IF 5.535) Pub Date : 2020-11-21
    Haofeng Zhang; Yinduo Wang; Yang Long; Longzhi Yang; Ling Shao

    Zero Shot Learning (ZSL) aims to classify images of unseen target classes by transferring knowledge from source classes through semantic embeddings. The core of ZSL research is to embed both visual representation of object instance and semantic description of object class into a joint latent space and learn cross-modal (visual and semantic) latent representations. However, the learned representations

    更新日期:2020-12-02
  • Episodic memory governs choices: An RNN-based reinforcement learning model for decision-making task
    Neural Netw. (IF 5.535) Pub Date : 2020-11-18
    Xiaohan Zhang; Lu Liu; Guodong Long; Jing Jiang; Shenquan Liu

    Typical methods to study cognitive function are to record the electrical activities of animal neurons during the training of animals performing behavioral tasks. A key problem is that they fail to record all the relevant neurons in the animal brain. To alleviate this problem, we develop an RNN-based Actor–Critic framework, which is trained through reinforcement learning (RL) to solve two tasks analogous

    更新日期:2020-12-01
  • Bridging multimedia heterogeneity gap via Graph Representation Learning for cross-modal retrieval
    Neural Netw. (IF 5.535) Pub Date : 2020-11-28
    Qingrong Cheng; Xiaodong Gu

    Information retrieval among different modalities becomes a significant issue with many promising applications. However, inconsistent feature representation of various multimedia data causes the “heterogeneity gap” among various modalities, which is a challenge in cross-modal retrieval. For bridging the “heterogeneity gap,” the popular methods attempt to project the original data into a common representation

    更新日期:2020-12-01
  • A brain-inspired network architecture for cost-efficient object recognition in shallow hierarchical neural networks
    Neural Netw. (IF 5.535) Pub Date : 2020-11-28
    Youngjin Park; Seungdae Baek; Se-Bum Paik

    The brain successfully performs visual object recognition with a limited number of hierarchical networks that are much shallower than artificial deep neural networks (DNNs) that perform similar tasks. Here, we show that long-range horizontal connections (LRCs), often observed in the visual cortex of mammalian species, enable such a cost-efficient visual object recognition in shallow neural networks

    更新日期:2020-12-01
  • Effect of diverse recoding of granule cells on optokinetic response in a cerebellar ring network with synaptic plasticity
    Neural Netw. (IF 5.535) Pub Date : 2020-11-28
    Sang-Yoon Kim; Woochang Lim

    We consider a cerebellar ring network for the optokinetic response (OKR), and investigate the effect of diverse recoding of granule (GR) cells on OKR by varying the connection probability pc from Golgi to GR cells. For an optimal value of pc∗(=0.06), individual GR cells exhibit diverse spiking patterns which are in-phase, anti-phase, or complex out-of-phase with respect to their population-averaged

    更新日期:2020-12-01
  • Approximation rates for neural networks with encodable weights in smoothness spaces
    Neural Netw. (IF 5.535) Pub Date : 2020-11-27
    Ingo Gühring; Mones Raslan

    We examine the necessary and sufficient complexity of neural networks to approximate functions from different smoothness spaces under the restriction of encodable network weights. Based on an entropy argument, we start by proving lower bounds for the number of nonzero encodable weights for neural network approximation in Besov spaces, Sobolev spaces and more. These results are valid for all sufficiently

    更新日期:2020-11-27
  • Necessary conditions for STDP-based pattern recognition learning in a memristive spiking neural network
    Neural Netw. (IF 5.535) Pub Date : 2020-11-27
    V.A. Demin; D.V. Nekhaev; I.A. Surazhevsky; K.E. Nikiruy; A.V. Emelyanov; S.N. Nikolaev; V.V. Rylkov; M.V. Kovalchuk

    This work is aimed to study experimental and theoretical approaches for searching effective local training rules for unsupervised pattern recognition by high-performance memristor-based Spiking Neural Networks (SNNs). First, the possibility of weight change using Spike-Timing-Dependent Plasticity (STDP) is demonstrated with a pair of hardware analog neurons connected through a (CoFeB)x(LiNbO3)1−x nanocomposite

    更新日期:2020-11-27
  • Generating photo-realistic training data to improve face recognition accuracy
    Neural Netw. (IF 5.535) Pub Date : 2020-11-27
    Daniel Sáez Trigueros; Li Meng; Margaret Hartnett

    Face recognition has become a widely adopted biometric in forensics, security and law enforcement thanks to the high accuracy achieved by systems based on convolutional neural networks (CNNs). However, to achieve good performance, CNNs need to be trained with very large datasets which are not always available. In this paper we investigate the feasibility of using synthetic data to augment face datasets

    更新日期:2020-11-27
  • Deep-learned spike representations and sorting via an ensemble of auto-encoders
    Neural Netw. (IF 5.535) Pub Date : 2020-11-27
    Junsik Eom; In Yong Park; Sewon Kim; Hanbyol Jang; Sanggeon Park; Yeowool Huh; Dosik Hwang

    Spike sorting refers to the technique of detecting signals generated by single neurons from multi-neuron recordings and is a valuable tool for analyzing the relationships between individual neuronal activity patterns and specific behaviors. Since the precision of spike sorting affects all subsequent analyses, sorting accuracy is critical. Many semi-automatic to fully-automatic spike sorting algorithms

    更新日期:2020-11-27
  • Learning sparse and meaningful representations through embodiment
    Neural Netw. (IF 5.535) Pub Date : 2020-11-23
    Viviane Clay; Peter König; Kai-Uwe Kühnberger; Gordon Pipa

    How do humans acquire a meaningful understanding of the world with little to no supervision or semantic labels provided by the environment? Here we investigate embodiment with a closed loop between action and perception as one key component in this process. We take a close look at the representations learned by a deep reinforcement learning agent that is trained with high-dimensional visual observations

    更新日期:2020-11-23
  • DMMAN: A two-stage audio–visual fusion framework for sound separation and event localization
    Neural Netw. (IF 5.535) Pub Date : 2020-11-11
    Ruihan Hu; Songbing Zhou; Zhi Ri Tang; Sheng Chang; Qijun Huang; Yisen Liu; Wei Han; Edmond Q. Wu

    Videos are used widely as the media platforms for human beings to touch the physical change of the world. However, we always receive the mixed sound from the multiple sound objects, and cannot distinguish and localize the sounds as the separate entities in videos. In order to solve this problem, a model named the Deep Multi-Modal Attention Network (DMMAN), is established to model the unconstrained

    更新日期:2020-11-22
  • ClsGAN: Selective Attribute Editing Model based on Classification Adversarial Network
    Neural Netw. (IF 5.535) Pub Date : 2020-11-10
    Ying Liu; Heng Fan; Fuchuan Ni; Jinhai Xiang

    Attribution editing has achieved remarkable progress in recent years owing to the encoder–decoder structure and generative adversarial network (GAN). However, it remains challenging to generate high-quality images with accurate attribute transformation. Attacking these problems, the work proposes a novel selective attribute editing model based on classification adversarial network (referred to as ClsGAN)

    更新日期:2020-11-22
  • Distant Supervision Relation Extraction via adaptive dependency-path and additional knowledge graph supervision
    Neural Netw. (IF 5.535) Pub Date : 2020-11-21
    Yong Shi; Yang Xiao; Pei Quan; MingLong Lei; Lingfeng Niu

    Relation Extraction systems train an extractor by aligning relation instances in Knowledge Base with a large amount of labeled corpora. Since the labeled datasets are very expensive, Distant Supervision Relation Extraction (DSRE) utilizes rough corpus annotated with Knowledge Graph to reduce the cost of acquisition. Nevertheless, the data noise problem limits the performance of the DSRE. Dependency

    更新日期:2020-11-22
  • Consensus guided incomplete multi-view spectral clustering
    Neural Netw. (IF 5.535) Pub Date : 2020-11-11
    Jie Wen; Huijie Sun; Lunke Fei; Jinxing Li; Zheng Zhang; Bob Zhang

    Incomplete multi-view clustering which aims to solve the difficult clustering challenge on incomplete multi-view data collected from diverse domains with missing views has drawn considerable attention in recent years. In this paper, we propose a novel method, called consensus guided incomplete multi-view spectral clustering (CGIMVSC), to address the incomplete clustering problem. Specifically, CGIMVSC

    更新日期:2020-11-21
  • An EEG channel selection method for motor imagery based brain–computer interface and neurofeedback using Granger causality
    Neural Netw. (IF 5.535) Pub Date : 2020-11-10
    Hesam Varsehi; S. Mohammad P. Firoozabadi

    Motor imagery (MI) brain–computer interface (BCI) and neurofeedback (NF) with electroencephalogram (EEG) signals are commonly used for motor function improvement in healthy subjects and to restore neurological functions in stroke patients. Generally, in order to decrease noisy and redundant information in unrelated EEG channels, channel selection methods are used which provide feasible BCI and NF implementations

    更新日期:2020-11-18
  • FMixCutMatch for semi-supervised deep learning
    Neural Netw. (IF 5.535) Pub Date : 2020-11-10
    Xiang Wei; Xiaotao Wei; Xiangyuan Kong; Siyang Lu; Weiwei Xing; Wei Lu

    Mixed sample augmentation (MSA) has witnessed great success in the research area of semi-supervised learning (SSL) and is performed by mixing two training samples as an augmentation strategy to effectively smooth the training space. Following the insights on the efficacy of cut-mix in particular, we propose FMixCut, an MSA that combines Fourier space-based data mixing (FMix) and the proposed Fourier

    更新日期:2020-11-18
  • Echo Memory-Augmented Network for time series classification
    Neural Netw. (IF 5.535) Pub Date : 2020-11-07
    Qianli Ma; Zhenjing Zheng; Wanqing Zhuang; Enhuan Chen; Jia Wei; Jiabing Wang

    Echo State Networks (ESNs) are efficient recurrent neural networks (RNNs) which have been successfully applied to time series modeling tasks. However, ESNs are unable to capture the history information far from the current time step, since the echo state at the present step of ESNs mostly impacted by the previous one. Thus, ESN may have difficulty in capturing the long-term dependencies of temporal

    更新日期:2020-11-18
  • Adversarial symmetric GANs: Bridging adversarial samples and adversarial networks
    Neural Netw. (IF 5.535) Pub Date : 2020-11-06
    Faqiang Liu; Mingkun Xu; Guoqi Li; Jing Pei; Luping Shi; Rong Zhao

    Generative adversarial networks have achieved remarkable performance on various tasks but suffer from training instability. Despite many training strategies proposed to improve training stability, this issue remains as a challenge. In this paper, we investigate the training instability from the perspective of adversarial samples and reveal that adversarial training on fake samples is implemented in

    更新日期:2020-11-17
  • PM2.5 concentration modeling and prediction by using temperature-based deep belief network
    Neural Netw. (IF 5.535) Pub Date : 2020-11-05
    Haixia Xing; Gongming Wang; Caixia Liu; Minghe Suo

    Air quality prediction is a global hot issue, and PM2.5 is an important factor affecting air quality. Due to complicated causes of formation, PM2.5 prediction is a thorny and challenging task. In this paper, a novel deep learning model named temperature-based deep belief networks (TDBN) is proposed to predict the daily concentrations of PM2.5 for the next day. Firstly, the location of PM2.5 concentration

    更新日期:2020-11-17
  • FPGAN: Face de-identification method with generative adversarial networks for social robots
    Neural Netw. (IF 5.535) Pub Date : 2020-09-20
    Jiacheng Lin; Yang Li; Guanci Yang

    In this paper, we propose a new face de-identification method based on generative adversarial network (GAN) to protect visual facial privacy, which is an end-to-end method (herein, FPGAN). First, we propose FPGAN and mathematically prove its convergence. Then, a generator with an improved U-Net is used to enhance the quality of the generated image, and two discriminators with a seven-layer network

    更新日期:2020-11-17
  • Gradient-based training and pruning of radial basis function networks with an application in materials physics
    Neural Netw. (IF 5.535) Pub Date : 2020-11-02
    Jussi Määttä; Viacheslav Bazaliy; Jyri Kimari; Flyura Djurabekova; Kai Nordlund; Teemu Roos

    Many applications, especially in physics and other sciences, call for easily interpretable and robust machine learning techniques. We propose a fully gradient-based technique for training radial basis function networks with an efficient and scalable open-source implementation. We derive novel closed-form optimization criteria for pruning the models for continuous as well as binary data which arise

    更新日期:2020-11-16
  • Robust facial landmark detection by cross-order cross-semantic deep network
    Neural Netw. (IF 5.535) Pub Date : 2020-11-16
    Jun Wan; Zhihui Lai; Linlin Shen; Jie Zhou; Can Gao; Gang Xiao; Xianxu Hou

    Recently, convolutional neural networks (CNNs)-based facial landmark detection methods have achieved great success. However, most of existing CNN-based facial landmark detection methods have not attempted to activate multiple correlated facial parts and learn different semantic features from them that they can not accurately model the relationships among the local details and can not fully explore

    更新日期:2020-11-16
  • AutoTune: Automatically Tuning Convolutional Neural Networks for Improved Transfer Learning
    Neural Netw. (IF 5.535) Pub Date : 2020-10-27
    S.H. Shabbeer Basha; Sravan Kumar Vinakota; Viswanath Pulabaigari; Snehasis Mukherjee; Shiv Ram Dubey

    Transfer learning enables solving a specific task having limited data by using the pre-trained deep networks trained on large-scale datasets. Typically, while transferring the learned knowledge from source task to the target task, the last few layers are fine-tuned (re-trained) over the target dataset. However, these layers are originally designed for the source task that might not be suitable for

    更新日期:2020-11-12
  • Particle swarm optimized neural networks based local tracking control scheme of unknown nonlinear interconnected systems
    Neural Netw. (IF 5.535) Pub Date : 2020-11-11
    Bo Zhao; Fangchao Luo; Haowei Lin; Derong Liu

    In this paper, a local tracking control (LTC) scheme is developed via particle swarm optimized neural networks (PSONN) for unknown nonlinear interconnected systems. With the local input–output data, a local neural network identifier is constructed to approximate the local input gain matrix and the mismatched interconnection, which are utilized to derive the LTC. To solve the local Hamilton–Jacobi-Bellman

    更新日期:2020-11-12
  • Efficient architecture for deep neural networks with heterogeneous sensitivity
    Neural Netw. (IF 5.535) Pub Date : 2020-11-10
    Hyunjoong Cho; Jinhyeok Jang; Chanhyeok Lee; Seungjoon Yang

    In this study, we present a neural network that consists of nodes with heterogeneous sensitivity. Each node in a network is assigned a variable that determines the sensitivity with which it learns to perform a given task. The network is trained via a constrained optimization that maximizes the sparsity of the sensitivity variables while ensuring optimal network performance. As a result, the network

    更新日期:2020-11-12
  • Unsupervised feature learning for self-tuning neural networks
    Neural Netw. (IF 5.535) Pub Date : 2020-10-22
    Jongbin Ryu; Ming-Hsuan Yang; Jongwoo Lim

    In recent years transfer learning has attracted much attention due to its ability to adapt a well-trained model from one domain to another. Fine-tuning is one of the most widely-used methods which exploit a small set of labeled data in the target domain for adapting the network. Including a few methods using the labeled data in the source domain, most transfer learning methods require labeled datasets

    更新日期:2020-11-06
  • Improved approach to the problem of the global Mittag-Leffler synchronization for fractional-order multidimension-valued BAM neural networks based on new inequalities
    Neural Netw. (IF 5.535) Pub Date : 2020-10-21
    Jianying Xiao; Shouming Zhong; Shiping Wen

    This paper studies the problem of the global Mittag-Leffler synchronization for fractional-order multidimension-valued BAM neural networks (FOMVBAMNNs) with general activation functions (AFs). First, the unified model is established for the researched systems of FOMVBAMNNs which can be turned into the corresponding multidimension-valued systems as long as the state variables, the connection weights

    更新日期:2020-11-02
  • Low Rank Regularization: A review
    Neural Netw. (IF 5.535) Pub Date : 2020-10-31
    Zhanxuan Hu; Feiping Nie; Rong Wang; Xuelong Li

    Low Rank Regularization (LRR), in essence, involves introducing a low rank or approximately low rank assumption to target we aim to learn, which has achieved great success in many data analysis tasks. Over the last decade, much progress has been made in theories and applications. Nevertheless, the intersection between these two lines is rare. In order to construct a bridge between practical applications

    更新日期:2020-11-02
  • Learning interaction dynamics with an interactive LSTM for conversational sentiment analysis
    Neural Netw. (IF 5.535) Pub Date : 2020-10-21
    Yazhou Zhang; Prayag Tiwari; Dawei Song; Xiaoliu Mao; Panpan Wang; Xiang Li; Hari Mohan Pandey

    Conversational sentiment analysis is an emerging, yet challenging subtask of the sentiment analysis problem. It aims to discover the affective state and sentimental change in each person in a conversation based on their opinions. There exists a wealth of interaction information that affects speaker sentiment in conversations. However, existing sentiment analysis approaches are insufficient in dealing

    更新日期:2020-10-29
  • Multiple graphs learning with a new weighted tensor nuclear norm
    Neural Netw. (IF 5.535) Pub Date : 2020-10-20
    Deyan Xie; Quanxue Gao; Siyang Deng; Xiaojun Yang; Xinbo Gao

    As an effective convex relaxation of the rank minimization model, the tensor nuclear norm minimization based multi-view clustering methods have been attracting more and more interest in recent years. However, most existing clustering methods regularize each singular value equally, restricting their capability and flexibility in tackling many practical problems, where the singular values should be treated

    更新日期:2020-10-29
  • CEGAN: Classification Enhancement Generative Adversarial Networks for unraveling data imbalance problems
    Neural Netw. (IF 5.535) Pub Date : 2020-10-17
    Sungho Suh; Haebom Lee; Paul Lukowicz; Yong Oh Lee

    The data imbalance problem in classification is a frequent but challenging task. In real-world datasets, numerous class distributions are imbalanced and the classification result under such condition reveals extreme bias in the majority data class. Recently, the potential of GAN as a data augmentation method on minority data has been studied. In this paper, we propose a classification enhancement generative

    更新日期:2020-10-29
  • Prespecified-time synchronization of switched coupled neural networks via smooth controllers
    Neural Netw. (IF 5.535) Pub Date : 2020-10-16
    Shao Shao; Xiaoyang Liu; Jinde Cao

    This paper considers the prespecified-time synchronization issue of switched coupled neural networks (SCNNs) under some smooth controllers. Different from the traditional finite-time synchronization (FTS), the synchronization time obtained in this paper is independent of control gains, initial values or network topology, which can be pre-set as to the task requirements. Moreover, unlike the existing

    更新日期:2020-10-29
  • Structural plasticity on an accelerated analog neuromorphic hardware system
    Neural Netw. (IF 5.535) Pub Date : 2020-10-12
    Sebastian Billaudelle; Benjamin Cramer; Mihai A. Petrovici; Korbinian Schreiber; David Kappel; Johannes Schemmel; Karlheinz Meier

    In computational neuroscience, as well as in machine learning, neuromorphic devices promise an accelerated and scalable alternative to neural network simulations. Their neural connectivity and synaptic capacity depend on their specific design choices, but is always intrinsically limited. Here, we present a strategy to achieve structural plasticity that optimizes resource allocation under these constraints

    更新日期:2020-10-29
  • Model-free motion control of continuum robots based on a zeroing neurodynamic approach
    Neural Netw. (IF 5.535) Pub Date : 2020-10-19
    Ning Tan; Peng Yu; Xinyu Zhang; Tao Wang

    As a result of inherent flexibility and structural compliance, continuum robots have great potential in practical applications and are attracting more and more attentions. However, these characteristics make it difficult to acquire the accurate kinematics of continuum robots due to uncertainties, deformation and external loads. This paper introduces a method based on a zeroing neurodynamic approach

    更新日期:2020-10-29
  • Reverse graph self-attention for target-directed atomic importance estimation
    Neural Netw. (IF 5.535) Pub Date : 2020-10-08
    Gyoung S. Na; Hyun Woo Kim

    Estimating the importance of each atom in a molecule is one of the most appealing and challenging problems in chemistry, physics, and materials science. The most common way to estimate the atomic importance is to compute the electronic structure using density functional theory (DFT), and then to interpret it using domain knowledge of human experts. However, this conventional approach is impractical

    更新日期:2020-10-17
  • An improved Lyapunov functional with application to stability of Cohen–Grossberg neural networks of neutral-type with multiple delays
    Neural Netw. (IF 5.535) Pub Date : 2020-10-12
    Ozlem Faydasicok

    The essential objective of this research article is to investigate stability issue of neutral-type Cohen–Grossberg neural networks involving multiple time delays in states of neurons and multiple neutral delays in time derivatives of states of neurons in the network. By exploiting a modified and improved version of a previously introduced Lyapunov functional, a new sufficient stability criterion is

    更新日期:2020-10-15
  • Self-grouping convolutional neural networks
    Neural Netw. (IF 5.535) Pub Date : 2020-09-17
    Qingbei Guo; Xiao-Jun Wu; Josef Kittler; Zhiquan Feng

    Although group convolution operators are increasingly used in deep convolutional neural networks to improve the computational efficiency and to reduce the number of parameters, most existing methods construct their group convolution architectures by a predefined partitioning of the filters of each convolutional layer into multiple regular filter groups with an equal spatial group size and data-independence

    更新日期:2020-10-11
  • Latent Dirichlet allocation based generative adversarial networks
    Neural Netw. (IF 5.535) Pub Date : 2020-09-21
    Lili Pan; Shen Cheng; Jian Liu; Peijun Tang; Bowen Wang; Yazhou Ren; Zenglin Xu

    Generative adversarial networks have been extensively studied in recent years and powered a wide range of applications, ranging from image generation, image-to-image translation, to text-to-image generation, and visual recognition. These methods typically model the mapping from latent space to image with single or multiple generators. However, they have obvious drawbacks: (i) ignoring the multi-modal

    更新日期:2020-10-11
  • Lower dimensional kernels for video discriminators
    Neural Netw. (IF 5.535) Pub Date : 2020-09-26
    Emmanuel Kahembwe; Subramanian Ramamoorthy

    This work presents an analysis of the discriminators used in Generative Adversarial Networks (GANs) for Video. We show that unconstrained video discriminator architectures induce a loss surface with high curvature which make optimization difficult. We also show that this curvature becomes more extreme as the maximal kernel dimension of video discriminators increases. With these observations in hand

    更新日期:2020-10-11
  • AMD-GAN: Attention encoder and multi-branch structure based generative adversarial networks for fundus disease detection from scanning laser ophthalmoscopy images
    Neural Netw. (IF 5.535) Pub Date : 2020-09-17
    Hai Xie; Haijun Lei; Xianlu Zeng; Yejun He; Guozhen Chen; Ahmed Elazab; Guanghui Yue; Jiantao Wang; Guoming Zhang; Baiying Lei

    The scanning laser ophthalmoscopy (SLO) has become an important tool for the determination of peripheral retinal pathology, in recent years. However, the collected SLO images are easily interfered by the eyelash and frame of the devices, which heavily affect the key feature extraction of the images. To address this, we propose a generative adversarial network called AMD-GAN based on the attention encoder

    更新日期:2020-10-11
  • Human interaction behavior modeling using Generative Adversarial Networks
    Neural Netw. (IF 5.535) Pub Date : 2020-09-30
    Yusuke Nishimura; Yutaka Nakamura; Hiroshi Ishiguro

    Recently, considerable research has focused on personal assistant robots, and robots capable of rich human-like communication are expected. Among humans, non-verbal elements contribute to effective and dynamic communication. However, people use a wide range of diverse gestures, and a robot capable of expressing various human gestures has not been realized. In this study, we address human behavior modeling

    更新日期:2020-10-11
  • Event-triggered impulsive synchronization of discrete-time coupled neural networks with stochastic perturbations and multiple delays
    Neural Netw. (IF 5.535) Pub Date : 2020-09-22
    Huiyuan Li; Jian-an Fang; Xiaofan Li; Leszek Rutkowski; Tingwen Huang

    This paper deals with the synchronization for discrete-time coupled neural networks (DTCNNs), in which stochastic perturbations and multiple delays are simultaneously involved. The multiple delays mean that both discrete time-varying delays and distributed delays are included. Time-triggered impulsive control (TTIC) is proposed to investigate the synchronization issue of the DTCNNs based on the recently

    更新日期:2020-10-05
  • On the robustness of skeleton detection against adversarial attacks
    Neural Netw. (IF 5.535) Pub Date : 2020-09-28
    Xiuxiu Bai; Ming Yang; Zhe Liu

    Human perception of an object’s skeletal structure is particularly robust to diverse perturbations of shape. This skeleton representation possesses substantial advantages for parts-based and invariant shape encoding, which is essential for object recognition. Multiple deep learning-based skeleton detection models have been proposed, while their robustness to adversarial attacks remains unclear. (1) This

    更新日期:2020-10-04
  • High-dimensional dynamics of generalization error in neural networks
    Neural Netw. (IF 5.535) Pub Date : 2020-09-05
    Madhu S. Advani; Andrew M. Saxe; Haim Sompolinsky

    We perform an analysis of the average generalization dynamics of large neural networks trained using gradient descent. We study the practically-relevant “high-dimensional” regime where the number of free parameters in the network is on the order of or even larger than the number of examples in the dataset. Using random matrix theory and exact solutions in linear models, we derive the generalization

    更新日期:2020-10-04
  • Neurodynamical classifiers with low model complexity
    Neural Netw. (IF 5.535) Pub Date : 2020-08-27
    Himanshu Pant; Sumit Soman; Jayadeva; Amit Bhaya

    The recently proposed Minimal Complexity Machine (MCM) finds a hyperplane classifier by minimizing an upper bound on the Vapnik–Chervonenkis (VC) dimension. The VC dimension measures the capacity or model complexity of a learning machine. Vapnik’s risk formula indicates that models with smaller VC dimension are expected to show improved generalization. On many benchmark datasets, the MCM generalizes

    更新日期:2020-10-02
  • Deconvolutional neural network for image super-resolution
    Neural Netw. (IF 5.535) Pub Date : 2020-09-23
    Feilong Cao; Kaixuan Yao; Jiye Liang

    This study builds a fully deconvolutional neural network (FDNN) and addresses the problem of single image super-resolution (SISR) by using the FDNN. Although SISR using deep neural networks has been a major research focus, the problem of reconstructing a high resolution (HR) image with an FDNN has received little attention. A few recent approaches toward SISR are to embed deconvolution operations into

    更新日期:2020-09-30
  • Learning to select actions shapes recurrent dynamics in the corticostriatal system
    Neural Netw. (IF 5.535) Pub Date : 2020-09-19
    Christian D. Márton; Simon R. Schultz; Bruno B. Averbeck

    Learning to select appropriate actions based on their values is fundamental to adaptive behavior. This form of learning is supported by fronto-striatal systems. The dorsal-lateral prefrontal cortex (dlPFC) and the dorsal striatum (dSTR), which are strongly interconnected, are key nodes in this circuitry. Substantial experimental evidence, including neurophysiological recordings, have shown that neurons

    更新日期:2020-09-28
  • Dual-regression model for visual tracking
    Neural Netw. (IF 5.535) Pub Date : 2020-09-24
    Xin Li; Qiao Liu; Nana Fan; Zikun Zhou; Zhenyu He; Xiao-yuan Jing

    Existing regression based tracking methods built on correlation filter model or convolution model do not take both accuracy and robustness into account at the same time. In this paper, we propose a dual-regression framework comprising a discriminative fully convolutional module and a fine-grained correlation filter component for visual tracking. The convolutional module trained in a classification

    更新日期:2020-09-28
  • Hybrid tensor decomposition in neural network compression
    Neural Netw. (IF 5.535) Pub Date : 2020-09-19
    Bijiao Wu; Dingheng Wang; Guangshe Zhao; Lei Deng; Guoqi Li

    Deep neural networks (DNNs) have enabled impressive breakthroughs in various artificial intelligence (AI) applications recently due to its capability of learning high-level features from big data. However, the current demand of DNNs for computational resources especially the storage consumption is growing due to that the increasing sizes of models are being required for more and more complicated applications

    更新日期:2020-09-22
  • GP-GAN: Brain tumor growth prediction using stacked 3D generative adversarial networks from longitudinal MR Images
    Neural Netw. (IF 5.535) Pub Date : 2020-09-17
    Ahmed Elazab; Changmiao Wang; Syed Jamal Safdar Gardezi; Hongmin Bai; Qingmao Hu; Tianfu Wang; Chunqi Chang; Baiying Lei

    Brain tumors are one of the major common causes of cancer-related death, worldwide. Growth prediction of these tumors, particularly gliomas which are the most dominant type, can be quite useful to improve treatment planning, quantify tumor aggressiveness, and estimate patients’ survival time towards precision medicine. Studying tumor growth prediction basically requires multiple time points of single

    更新日期:2020-09-22
  • Multi-label zero-shot learning with graph convolutional networks
    Neural Netw. (IF 5.535) Pub Date : 2020-09-21
    Guangjin Ou; Guoxian Yu; Carlotta Domeniconi; Xuequan Lu; Xiangliang Zhang

    The goal of zero-shot learning (ZSL) is to build a classifier that recognizes novel categories with no corresponding annotated training data. The typical routine is to transfer knowledge from seen classes to unseen ones by learning a visual-semantic embedding. Existing multi-label zero-shot learning approaches either ignore correlations among labels, suffer from large label combinations, or learn the

    更新日期:2020-09-22
  • High-content image generation for drug discovery using generative adversarial networks
    Neural Netw. (IF 5.535) Pub Date : 2020-09-20
    Shaista Hussain; Ayesha Anees; Ankit Das; Binh P. Nguyen; Mardiana Marzuki; Shuping Lin; Graham Wright; Amit Singhal

    Immense amount of high-content image data generated in drug discovery screening requires computationally driven automated analysis. Emergence of advanced machine learning algorithms, like deep learning models, has transformed the interpretation and analysis of imaging data. However, deep learning methods generally require large number of high-quality data samples, which could be limited during preclinical

    更新日期:2020-09-22
  • Exponential synchronization of neural networks with time-varying delays and stochastic impulses
    Neural Netw. (IF 5.535) Pub Date : 2020-09-19
    Yifan Sun; Lulu Li; Xiaoyang Liu

    This paper concentrates on the exponential synchronization problem of the delayed neural networks (DNNs) with stochastic impulses. First, the impulsive Halanay differential inequality is further extended to the case that the impulsive strengths are random variables. Then, based on the generalized inequalities, synchronization criteria are respectively proposed for DNNs with two kinds of stochastic

    更新日期:2020-09-22
  • Real-time gun detection in CCTV: An open problem
    Neural Netw. (IF 5.535) Pub Date : 2020-09-17
    Jose L. Salazar González; Carlos Zaccaro; Juan A. Álvarez-García; Luis M. Soria Morillo; Fernando Sancho Caparrini

    Object detectors have improved in recent years, obtaining better results and faster inference time. However, small object detection is still a problem that has not yet a definitive solution. The autonomous weapons detection on Closed-circuit television (CCTV) has been studied recently, being extremely useful in the field of security, counter-terrorism, and risk mitigation. This article presents a new

    更新日期:2020-09-22
  • Analysis of the transferability and robustness of GANs evolved for Pareto set approximations.
    Neural Netw. (IF 5.535) Pub Date : 2020-09-16
    Unai Garciarena,Alexander Mendiburu,Roberto Santana

    The generative adversarial network (GAN) is a good example of a strong-performing, neural network-based generative model, even though it does have some drawbacks of its own. Mode collapsing and the difficulty in finding the optimal network structure are two of the most concerning issues. In this paper, we address these two issues at the same time by proposing a neuro-evolutionary approach with an agile

    更新日期:2020-09-20
  • Boundary Mittag-Leffler stabilization of fractional reaction-diffusion cellular neural networks.
    Neural Netw. (IF 5.535) Pub Date : 2020-09-15
    Xiao-Zhen Liu,Ze-Tao Li,Kai-Ning Wu

    Mittag-Leffler stabilization is studied for fractional reaction–diffusion cellular neural networks (FRDCNNs) in this paper. Different from previous literature, the FRDCNNs in this paper are high-dimensional systems, and boundary control and observed-based boundary control are both used to make FRDCNNs achieve Mittag-Leffler stability. First, a state-dependent boundary controller is designed when system

    更新日期:2020-09-16
  • Image manipulation with natural language using Two-sided Attentive Conditional Generative Adversarial Network
    Neural Netw. (IF 5.535) Pub Date : 2020-09-12
    Dawei Zhu; Aditya Mogadala; Dietrich Klakow

    Altering the content of an image with photo editing tools is a tedious task for an inexperienced user. Especially, when modifying the visual attributes of a specific object in an image without affecting other constituents such as background etc. To simplify the process of image manipulation and to provide more control to users, it is better to utilize a simpler interface like natural language. It also

    更新日期:2020-09-12
  • Low-rank tensor constrained co-regularized multi-view spectral clustering.
    Neural Netw. (IF 5.535) Pub Date : 2020-09-05
    Huiling Xu,Xiangdong Zhang,Wei Xia,Quanxue Gao,Xinbo Gao

    Due to the efficiency of exploiting relationships and complex structures hidden in multi-views data, graph-oriented clustering methods have achieved remarkable progress in recent years. But most existing graph-based spectral methods still have the following demerits: (1) They regularize each view equally, which does not make sense in real applications. (2) By employing different norms, most existing

    更新日期:2020-09-11
  • A direct approach for function approximation on data defined manifolds.
    Neural Netw. (IF 5.535) Pub Date : 2020-08-25
    H N Mhaskar

    In much of the literature on function approximation by deep networks, the function is assumed to be defined on some known domain, such as a cube or a sphere. In practice, the data might not be dense on these domains, and therefore, the approximation theory results are observed to be too conservative. In manifold learning, one assumes instead that the data is sampled from an unknown manifold; i.e.,

    更新日期:2020-09-11
  • Efficient search for informational cores in complex systems: Application to brain networks.
    Neural Netw. (IF 5.535) Pub Date : 2020-08-28
    Jun Kitazono,Ryota Kanai,Masafumi Oizumi

    An important step in understanding the nature of the brain is to identify “cores” in the brain network, where brain areas strongly interact with each other. Cores can be considered as essential sub-networks for brain functions. In the last few decades, an information-theoretic approach to identifying cores has been developed. In this approach, interactions between parts are measured by an information

    更新日期:2020-09-10
Contents have been reproduced by permission of the publishers.
导出