检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Luo, Xinyu Musco, Christopher Widdershoven, Cas Department of Computer Science Purdue University Indiana United States Tandon School of Engineering New York University New York United States State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

Finding the mode of a high dimensional probability distribution D is a fundamental algorithmic problem in statistics and data analysis. There has been particular interest in efficient methods for solving the problem when D is represented as a mixture model or kernel density estimate, although few algorithmic results with worst-case approximation and runtime guarantees are known. In this work, we significantly generalize a result of (Lee et al., 2021) on mode approximation for Gaussian mixture models. We develop randomized dimensionality reduction methods for mixtures involving a broader class of kernels, including the popular logistic, sigmoid, and generalized Gaussian kernels. As in Lee et al.’s work, our dimensionality reduction results yield quasi-polynomial algorithms for mode finding with multiplicative accuracy (1 − ϵ) for any ϵ > 0. Moreover, when combined with gradient descent, they yield efficient practical heuristics for the problem. In addition to our positive results, we prove a hardness result for box kernels, showing that there is no polynomial time algorithm for finding the mode of a kernel density estimate, unless P = NP. Obtaining similar hardness results for kernels used in practice (like Gaussian or logistic kernels) is an interesting future direction. Copyright © 2023, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

CMG-Net: An End-to-End Contact-Based Multi-Finger Dexterous Grasping Network

arXiv

引用

arXiv 2023年

作者： Wei, Mingze Huang, Yaomin Xu, Zhiyuan Liu, Ning Che, Zhengping Zhang, Xinyu Shen, Chaomin Feng, Feifei Shan, Chun Tang, Jian School of Software Engineering East China Normal University China School of Computer Science East China Normal University China Midea Group China School of Electronics and Information Guangdong Polytechnic Normal University China

In this paper, we propose a novel representation for grasping using contacts between multi-finger robotic hands and objects to be manipulated. This representation significantly reduces the prediction dimensions and accelerates the learning process. We present an effective end-to-end network, CMG-Net, for grasping unknown objects in a cluttered environment by efficiently predicting multi-finger grasp poses and hand configurations from a single-shot point cloud. Moreover, we create a synthetic grasp dataset that consists of five thousand cluttered scenes, 80 object categories, and 20 million annotations. We perform a comprehensive empirical study and demonstrate the effectiveness of our grasping representation and CMG-Net. Our work significantly outperforms the state-of-the-art for three-finger robotic hands. We also demonstrate that the model trained using synthetic data performs very well for real robots. Copyright © 2023, The Authors. All rights reserved.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

NOMABER: A Novel Framework for Multi-Type Abnormal Behaviour Recognition

NOMABER: A Novel Framework for Multi-Type Abnormal Behaviour...

引用

IEEE International Conference on Big Data

作者： Ao Wang Yongchen Yao Yuhan Yao Jinpeng Chen School of Computer Science (National Pilot Software Engineering School) Beijing University of Posts and Telecommunications Beijing P.R. China

ISBN: (纸本)9781665480468

Recently, using machine learning technology to realize abnormal behavior recognition in video surveillance to replace human monitoring has become a hot academic topic. In that case, constructing an efficient and unified framework for multi-type abnormal behavior recognition is a worthy topic in machine learning research. This research aims to design a lightweight recognition framework that can recognize various abnormal behaviors in real-time. We propose a Novel framewOrk for the Multi-type Abnormal BEhavior Recognition (NOMABER), which consists of three parts. Firstly, the improved image pre-processing module annotates the abnormal behaviors of image data sets. Secondly, the improved YOLOv5 module is used to identify the multi-type abnormal behaviors, and then the abnormal behaviors are classified by the output module. Finally, experiments on real data sets show that NOMABER is superior to the current methods of real-time performance, identification accuracy, and types of abnormal behaviors.

关键词： Training Image recognition Annotations Machine learning Big Data Video surveillance Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Stock market prediction based on machine learning and social sentiment analysis

TechRxiv

引用

TechRxiv 2023年

作者： Ghazanfar, Mustansar Ali Anwar, Madiha Lee, Sin Wee Qazi, Nadeem Karimi, Amin Jhanjhi, N.Z. Javed, Ali School of Architecture Computing and Engineering University of East London United Kingdom Deputy Head of School of Computing Arden University United Kingdom School of Computer Science SCS Taylor’s University Malaysia Department of Software Engineering UET Taxila Pakistan

Precise stock market prediction is crucial for investors, but the volatility of the stock market is influenced by multiple factors such as public sentiments, business news, and related product volatility. While several algorithms have been proposed to predict the stock exchange index based on historical data, they are not ideal as external factors play a critical role in market volatility. To address this issue, we proposed a machine learning model that incorporates historical data with external factors such as social media sentiments, oil and gold trends, and financial news data to enhance prediction accuracy. Our study used HPQ, IBM, ORCL, and MSFT stock market datasets to validate the effectiveness of the proposed model, including an analysis of the impact of Covid19 on companies. Our experimental results showed the highest accuracy of 87.2% using oil and sentiment datasets. Additionally, we identified that social media significantly affects IBM stocks, and the GBM (Gradient Boosting Classifier) classifier produced consistent results. © 2023, CC BY.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Incomplete Multi-View Representation Learning Through Anchor Graph-Based GCN and Information Bottleneck

Incomplete Multi-View Representation Learning Through Anchor...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zhenjiao Liu Xiao Wang Xiaodi Huang Guanlin Li Ke Sun Zhikui Chen School of Software Technology Dalian University of Technology Dalian China Samovar Telecom SudParis Institut Polytechnique de Paris Palaiseau France School of Computing Mathematics and Engineering Charles Sturt University Albury Australia School of Computer Science and Technology Dalian University of Technology

Real-world data often contain incomplete views with varying degrees of missing information. While there are existing methods for learning representations from such data, effectively utilizing all incomplete view data and ensuring robustness to different levels of completeness remains a challenging task. To address this problem, we propose a novel framework named IMRL-AGI. IMRL-AGI combines the anchor graph-based Graph Convolutional Network (GCN) and information bottleneck. Specifically, the framework starts by constructing an anchor graph to effectively captures the nonlinear information between instances. Next, an anchor graph-based GCN is designed to extract feature information from various views. IMRL-AGI maximizes the mutual information between the views obtained by the common representation and the anchor-graph-based GCN, ensuring the accurate extraction of view information. Furthermore, the minimization of mutual information is applied to promote diversity and reduce redundancy in the multi-view representation. Extensive experiments are conducted on several real-world datasets, and the results demonstrate the superiority of IMRL-AGI.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SceneGATE: Scene-Graph Based Co-Attention Networks for Text Visual Question Answering

arXiv

引用

arXiv 2022年

作者： Cao, Feiqi Luo, Siwen Nunez, Felipe Wen, Zean Poon, Josiah Han, Soyeon Caren School of Computer Science Faculty of Engineering University of Sydney CamperdownNSW2006 Australia Department of Computer Science and Software Engineering School of Physics Maths and Computing University of Western Australia CrawleyWA6009 Australia

Visual Question Answering (VQA) models fail catastrophically on questions related to the reading of text-carrying images. However, TextVQA aims to answer questions by understanding the scene texts in an image-question context, such as the brand name of a product or the time on a clock from an image. Most TextVQA approaches focus on objects and scene text detection, which are then integrated with the words in a question by a simple transformer encoder. The focus of these approaches is to use shared weights during the training of a multi-modal dataset, but it fails to capture the semantic relations between an image and a question. In this paper, we proposed a Scene Graph-Based Co-Attention Network (SceneGATE) for TextVQA, which reveals the semantic relations among the objects, the Optical Character Recognition (OCR) tokens and the question words. It is achieved by a TextVQA-based scene graph that discovers the underlying semantics of an image. We create a guided-attention module to capture the intra-modal interplay between the language and the vision as a guidance for inter-modal interactions. To permit explicit teaching of the relations between the two modalities, we propose and integrate two attention modules, namely a scene graph-based semantic relation-aware attention and a positional relation-aware attention. We conduct extensive experiments on two widely used benchmark datasets, Text-VQA and ST-VQA. It is shown that our SceneGATE method outperforms existing ones because of the scene graph and its attention modules. Copyright © 2022, The Authors. All rights reserved.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Better Diffusion Models Further Improve Adversarial Training

arXiv

引用

arXiv 2023年

作者： Wang, Zekai Pang, Tianyu Du, Chao Lin, Min Liu, Weiwei Yan, Shuicheng School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan University China Sea AI Lab

It has been recognized that the data generated by the denoising diffusion probabilistic model (DDPM) improves adversarial training. After two years of rapid development in diffusion models, a question naturally arises: can better diffusion models further improve adversarial training? This paper gives an affirmative answer by employing the most recent diffusion model (Karras et al., 2022) which has higher efficiency (∼ 20 sampling steps) and image quality (lower FID score) compared with DDPM. Our adversarially trained models achieve state-of-the-art performance on RobustBench using only generated data (no external datasets). Under the ∞norm threat model with ϵ = 8/255, our models achieve 70.69% and 42.67% robust accuracy on CIFAR-10 and CIFAR-100, respectively, i.e. improving upon previous state-of-the-art models by +4.58% and +8.03%. Under the 2-norm threat model with ϵ = 128/255, our models achieve 84.86% on CIFAR-10 (+4.44%). These results also beat previous works that use external data. We also provide compelling results on the SVHN and TinyImageNet datasets. Our code is at https://***/wzekai99/DM-Improves-AT. Copyright © 2023, The Authors. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Web3D Learning Framework for 3D Shape Retrieval Based on Hybrid Convolutional Neural Networks

引用

Tsinghua science and Technology 2020年第1期25卷 93-102页

作者： Wen Zhou Jinyuan Jia Chengxi Huang Yongqing Cheng School of Computer and Information Anhui Normal UniversityWuhu 241002China School of Software Engineering Tongji UniversityShanghai 201804China College of Electronics and Information Engineering Tongji UniversityShanghai 201804China School of Engineering and Computer Science University of HullHullHU6 7RXUK.

With the rapid development of Web3 D technologies, sketch-based model retrieval has become an increasingly important challenge, while the application of Virtual Reality and 3 D technologies has made shape retrieval of furniture over a web browser feasible. In this paper, we propose a learning framework for shape retrieval based on two Siamese VGG-16 Convolutional Neural Networks(CNNs), and a CNN-based hybrid learning algorithm to select the best view for a shape. In this algorithm, the AlexNet and VGG-16 CNN architectures are used to perform classification tasks and to extract features, respectively. In addition, a feature fusion method is used to measure the similarity relation of the output features from the two Siamese networks. The proposed framework can provide new alternatives for furniture retrieval in the Web3 D environment. The primary innovation is in the employment of deep learning methods to solve the challenge of obtaining the best view of 3 D furniture,and to address cross-domain feature learning problems. We conduct an experiment to verify the feasibility of the framework and the results show our approach to be superior in comparison to many mainstream state-of-the-art approaches.

关键词： Web3D sketch-based model retrieval Convolutional Neural Networks(CNNs) best view cross-domain

来源：评论

学校读者我要写书评

暂无评论

Chebyshev Polynomial Broad Learning System

Chebyshev Polynomial Broad Learning System

引用

2021 International Conference on Information, Cybernetics, and Computational Social Systems, ICCSS 2021

作者： Feng, Shuang Wang, Bingshu Philip Chen, C.L. Beijing Normal University School of Applied Mathematics Zhuhai China Northwestern Polytechnical University School of Software Suzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9781665402453

The broad learning system (BLS) has been attracting more and more attention due to its excellent property in the field of machine learning. A great deal of variants and hybrid structures of BLS have also been designed and developed for better performance in some specialized tasks. In this paper, the Chebyshev polynomials are introduced into the BLS to take advantage of their powerful approximation capability, where the feature windows are replaced by a set of Chebyshev polynomials. This new variant, named Chebyshev polynomial BLS (CPBLS), has a light structure with a reduction in computational complexity since the sparse autoencoder is removed. Instead, the dimension of each input sample is expended by n + 1 Chebyshev polynomials, mapping the original feature into a new feature space with higher dimension, which helps to classify the patterns in training. The proposed CPBLS is evaluated by some popular datasets from UCI and KEEL repositories, and it outperforms some representative neural networks and neuro-fuzzy models in terms of classification accuracy. The CPBLS also show some advantages over the recent developed compact fuzzy BLS (CFBLS) which indicates its great potential in future research and real-world applications. © 2021 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

A Heuristic-based Dynamic Scheduling and Routing Method for Industrial TSN Networks

A Heuristic-based Dynamic Scheduling and Routing Method for ...

引用

IEEE International Conference on Cyber Security and Cloud Computing (CSCloud)

作者： Honglong Chen Mindong Liu Jing Huang Zhiling Zheng Weihong Huang Yufeng Xiao School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology Xiangtan China Information Center Hunan Industry Polytechnic Changsha China

In the industrial environment, machines often need to reflect the anomaly detection results to the total control center in time, and the general industrial network can not achieve high real-time. In order to solve such challenges, a set of protocol standards developed by IEEE802.1 working group, namely Time-sensitive Networking (TSN), has been introduced into industrial networks. TSN can provide high real-time and reliability for data transmission, where the reliability is achieved by Frame duplication and Frame Elimination (FRER). In the realization process of FRER, it is necessary to determine the source node, destination node, and multiple disjoint paths to transmit redundant data. However, the transmission of these redundant traffic may result in the delay of other flows, and then affects the user experience. Therefore, it is very important to choose excellent redundant traffic paths to ensure reliability and reduce the impact on other flows. In the existing research, there are many dynamic scheduling and routing heuristics to determine the path, but they do not consider the influence of the location of the source node on the whole route scheduling. This paper proposes an improved dynamic scheduling and routing heuristic method, which takes the source node into account in the routing selection. In the flow test experiments of different magnitudes, it is found that the total delay of all flows is reduced by 1.4%-4.5% under the same magnitude of schedulability compared with Ant Colony Optimization.

关键词：

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：