Neural Processing Letters最新文献_第3页

On Stage-Wise Backpropagation for Improving Cheng’s Method for Fully Connected Cascade Networks 关于分阶段反向传播改进全连接级联网络的程氏方法

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-07-11 DOI: 10.1007/s11063-024-11655-4

Eiji Mizutani, Naoyuki Kubota, Tam Chi Truong

{"title":"On Stage-Wise Backpropagation for Improving Cheng’s Method for Fully Connected Cascade Networks","authors":"Eiji Mizutani, Naoyuki Kubota, Tam Chi Truong","doi":"10.1007/s11063-024-11655-4","DOIUrl":"https://doi.org/10.1007/s11063-024-11655-4","url":null,"abstract":"In this journal, Cheng has proposed a backpropagation (BP) procedure called BPFCC for deep fully connected cascaded (FCC) neural network learning in comparison with a neuron-by-neuron (NBN) algorithm of Wilamowski and Yu. Both BPFCC and NBN are designed to implement the Levenberg-Marquardt method, which requires an efficient evaluation of the Gauss-Newton (approximate Hessian) matrix (nabla textbf{r}^textsf{T} nabla textbf{r}), the cross product of the Jacobian matrix (nabla textbf{r}) of the residual vector (textbf{r}) in nonlinear least squares sense. Here, the dominant cost is to form (nabla textbf{r}^textsf{T} nabla textbf{r}) by rank updates on each data pattern. Notably, NBN is better than BPFCC for the multiple (q~!(>!1))-output FCC-learning when q rows (per pattern) of the Jacobian matrix (nabla textbf{r}) are evaluated; however, the dominant cost (for rank updates) is common to both BPFCC and NBN. The purpose of this paper is to present a new more efficient stage-wise BP procedure (for q-output FCC-learning) that reduces the dominant cost with no rows of (nabla textbf{r}) explicitly evaluated, just as standard BP evaluates the gradient vector (nabla textbf{r}^textsf{T} textbf{r}) with no explicit evaluation of any rows of the Jacobian matrix (nabla textbf{r}).","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"64 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-07-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141585797","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Detection Method of Manipulator Grasp Pose Based on RGB-D Image 基于 RGB-D 图像的机械手抓握姿势检测方法

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-07-09 DOI: 10.1007/s11063-024-11662-5

Cheng Huang, Zhen Pang, Jiazhong Xu

{"title":"Detection Method of Manipulator Grasp Pose Based on RGB-D Image","authors":"Cheng Huang, Zhen Pang, Jiazhong Xu","doi":"10.1007/s11063-024-11662-5","DOIUrl":"https://doi.org/10.1007/s11063-024-11662-5","url":null,"abstract":"In order to better solve the visual detection problem of manipulator grasping non-cooperative targets, we propose a method of grasp pose detection based on pixel point and feature fusion. By using the improved U2net network as the backbone for feature extraction and feature fusion of the input image, and the grasp prediction layer detects the grasp pose on each pixel. In order to adapt the U2net to grasp pose detection and improve its detection performance, we improve detection speed and control sampling depth by simplifying its network structure, while retaining some shallow features in feature fusion to enhance its feature extraction capability. We introduce depthwise separable convolution in the grasp prediction layer, further fusing the features extracted from the backbone to obtain predictive feature maps with stronger feature expressiveness. FocalLoss is selected as the loss function to solve the problem of unbalanced positive and negative samples in network training. We use the Cornell dataset for training and testing, perform pixel-level labeling on the image, and replace the labels that are not conducive to the actual grasping. This adaptation helps the dataset better suit the network training and testing while meeting the real-world grasping requirements of the manipulator. The evaluation results on image-wise and object-wise are 95.65% and 91.20% respectively, and the detection speed is 0.007 s/frame. We also used the method for actual manipulator grasping experiments. The results show that our method has improved accuracy and speed compared with previous methods, and has strong generalization ability and portability.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"39 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-07-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141574440","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

A Lightweight Task-Agreement Meta Learning for Low-Resource Speech Recognition 用于低资源语音识别的轻量级任务协议元学习

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-07-05 DOI: 10.1007/s11063-024-11661-6

Yaqi Chen, Hao Zhang, Wenlin Zhang, Dan Qu, Xukui Yang

引用次数: 0

PANet: Pluralistic Attention Network for Few-Shot Image Classification PANet：用于少镜头图像分类的多元注意网络

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-06-29 DOI: 10.1007/s11063-024-11638-5

Wenming Cao, Tianyuan Li, Qifan Liu, Zhiquan He

{"title":"PANet: Pluralistic Attention Network for Few-Shot Image Classification","authors":"Wenming Cao, Tianyuan Li, Qifan Liu, Zhiquan He","doi":"10.1007/s11063-024-11638-5","DOIUrl":"https://doi.org/10.1007/s11063-024-11638-5","url":null,"abstract":"Traditional deep learning methods require a large amount of labeled data for model training, which is laborious and costly in real word. Few-shot learning (FSL) aims to recognize novel classes with only a small number of labeled samples to address these challenges. We focus on metric-based few-shot learning with improvements in both feature extraction and metric method. In our work, we propose the Pluralistic Attention Network (PANet), a novel attention-oriented framework, involving both a local encoded intra-attention(LEIA) module and a global encoded reciprocal attention(GERA) module. The LEIA is designed to capture comprehensive local feature dependencies within every single sample. The GERA concentrates on the correlation between two samples and learns the discriminability of representations obtained from the LEIA. The two modules are complementary to each other and ensure the feature information within and between images can be fully utilized. Furthermore, we also design a dual-centralization (DC) cosine similarity to eliminate the disparity of data distribution in different dimensions and enhance the metric accuracy between support and query samples. Our method is thoroughly evaluated with extensive experiments, and the results demonstrate that with the contribution of each component, our model can achieve high-performance on four widely used few-shot classification benchmarks of miniImageNet, tieredImageNet, CUB-200-2011 and CIFAR-FS.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"81 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-06-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505306","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Exponential Stability of Impulsive Stochastic Neutral Neural Networks with Lévy Noise Under Non-Lipschitz Conditions 非 Lipschitz 条件下具有 Lévy 噪声的脉冲随机中性神经网络的指数稳定性

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-06-28 DOI: 10.1007/s11063-024-11663-4

Shuo Ma, Jiangman Li, Ruonan Liu, Qiang Li

引用次数: 0

Knowledge Graph-Aware Deep Interest Extraction Network on Sequential Recommendation 基于序列推荐的知识图谱感知深度兴趣提取网络

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-06-28 DOI: 10.1007/s11063-024-11665-2

Zhenhai Wang, Yuhao Xu, Zhiru Wang, Rong Fan, Yunlong Guo, Weimin Li

{"title":"Knowledge Graph-Aware Deep Interest Extraction Network on Sequential Recommendation","authors":"Zhenhai Wang, Yuhao Xu, Zhiru Wang, Rong Fan, Yunlong Guo, Weimin Li","doi":"10.1007/s11063-024-11665-2","DOIUrl":"https://doi.org/10.1007/s11063-024-11665-2","url":null,"abstract":"Sequential recommendation is the mainstream approach in the field of click-through-rate (CTR) prediction for modeling users’ behavior. This behavior implies the change of the user’s interest, and the goal of sequential recommendation is to capture this dynamic change. However, existing studies have focused on designing complex dedicated networks to capture user interests from user behavior sequences, while neglecting the use of auxiliary information. Recently, knowledge graph (KG) has gradually attracted the attention of researchers as a structured auxiliary information. Items and their attributes in the recommendation, can be mapped to knowledge triples in the KG. Therefore, the introduction of KG to recommendation can help us obtain more expressive item representations. Since KG can be considered a special type of graph, it is possible to use the graph neural network (GNN) to propagate the rich information contained in the KG into the item representation. Based on this idea, this paper proposes a recommendation method that uses KG as auxiliary information. The method first propagates the knowledge information in the KG using GNN to obtain a knowledge-rich item representation. Then the temporal features in the item sequence are extracted using a transformer for CTR prediction, namely the Knowledge Graph-Aware Deep Interest Extraction network (KGDIE). To evaluate the performance of this model, we conducted extensive experiments on two real datasets with different scenarios. The results showed that the KGDIE method could outperform several state-of-the-art baselines. The source code of our model is available at https://github.com/gylgyl123/kgdie.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"150 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-06-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141505308","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Gudermannian Neural Networks for Two-Point Nonlinear Singular Model Arising in the Thermal-Explosion Theory 热爆炸理论中出现的两点非线性奇异模型的古德曼神经网络

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-06-26 DOI: 10.1007/s11063-024-11512-4

Samara Fatima, Zulqurnain Sabir, Dumitru Baleanu, Sharifah E. Alhazmi

引用次数: 0

Adaptive Sliding Mode Fixed-/Preassigned-Time Synchronization of Stochastic Memristive Neural Networks with Mixed-Delays 具有混合延迟的随机记忆神经网络的自适应滑动模式固定/预分配时间同步化

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-06-21 DOI: 10.1007/s11063-024-11669-y

Jie Gao, Xiangyong Chen, Jianlong Qiu, Chunmei Wang, Tianyuan Jia

引用次数: 0

SS-CRE: A Continual Relation Extraction Method Through SimCSE-BERT and Static Relation Prototypes SS-CRE：通过 SimCSE-BERT 和静态关系原型的连续关系提取方法

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-06-20 DOI: 10.1007/s11063-024-11647-4

Jinguang Chen, Suyue Wang, Lili Ma, Bo Yang, Kaibing Zhang

{"title":"SS-CRE: A Continual Relation Extraction Method Through SimCSE-BERT and Static Relation Prototypes","authors":"Jinguang Chen, Suyue Wang, Lili Ma, Bo Yang, Kaibing Zhang","doi":"10.1007/s11063-024-11647-4","DOIUrl":"https://doi.org/10.1007/s11063-024-11647-4","url":null,"abstract":"Continual relation extraction aims to learn new relations from a continuous stream of data while avoiding forgetting old relations. Existing methods typically use the BERT encoder to obtain semantic embeddings, ignoring the fact that the vector representations suffer from anisotropy and uneven distribution. Furthermore, the relation prototypes are usually computed by memory samples directly, resulting in the model being overly sensitive to memory samples. To solve these problems, we propose a new continual relation extraction method. Firstly, we modified the basic structure of the sample encoder to generate uniformly distributed semantic embeddings using the supervised SimCSE-BERT to obtain richer sample information. Secondly, we introduced static relation prototypes and dynamically adjust their proportion with dynamic relation prototypes to adapt to the feature space. Lastly, through experimental analysis on the widely used FewRel and TACRED datasets, the results demonstrate that the proposed method effectively enhances semantic embeddings and relation prototypes, resulting in a further alleviation of catastrophic forgetting in the model. The code will be soon released at https://github.com/SuyueW/SS-CRE.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"23 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-06-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141520317","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

KGR: A Kernel-Mapping Based Group Recommender System Using Trust Relations KGR：使用信任关系的基于核映射的群体推荐系统

IF 3.1 4区计算机科学

Neural Processing Letters Pub Date : 2024-06-19 DOI: 10.1007/s11063-024-11639-4

Maryam Bukhari, Muazzam Maqsood, Farhan Aadil

{"title":"KGR: A Kernel-Mapping Based Group Recommender System Using Trust Relations","authors":"Maryam Bukhari, Muazzam Maqsood, Farhan Aadil","doi":"10.1007/s11063-024-11639-4","DOIUrl":"https://doi.org/10.1007/s11063-024-11639-4","url":null,"abstract":"A massive amount of information explosion over the internet has caused a possible difficulty of information overload. To overcome this, Recommender systems are systematic tools that are rapidly being employed in several domains such as movies, travel, E-commerce, and music. In the existing research, several methods have been proposed for single-user modeling, however, the massive rise of social connections potentially increases the significance of group recommender systems (GRS). A GRS is one that jointly recommends a list of items to a collection of individuals based on their interests. Moreover, the single-user model poses several challenges to recommender systems such as data sparsity, cold start, and long tail problems. On the contrary hand, another hotspot for group-based recommendation is the modeling of user preferences and interests based on the groups to which they belong using effective aggregation strategies. To address such issues, a novel “KGR” group recommender system based on user-trust relations is proposed in this study using kernel mapping techniques. In the proposed model, user-trust networks or relations are exploited to generate trust-based groups of users which is one of the important behavioral and social aspects. More precisely, in KGR the group kernels and group residual matrices are exploited as well as seeking a multi-linear mapping between encoded vectors of group-item interactions and probability density function indicating how groups will rate the items. Moreover, to emphasize the relevance of individual preferences of users in a group to which they belong, a hybrid approach is also suggested in which group kernels and individual user kernels are merged as additive and multiplicative models. Furthermore, the proposed KGR is validated on two different trust-based datasets including Film Trust and CiaoDVD. In addition, KGR outperforms with an RMSE value of 0.3306 and 0.3013 on FilmTrust and CiaoDVD datasets which are lower than the 1.8176 and 1.1092 observed with the original KMR.","PeriodicalId":51144,"journal":{"name":"Neural Processing Letters","volume":"116 1","pages":""},"PeriodicalIF":3.1,"publicationDate":"2024-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141520318","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0