检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Rokhsatyazdi, Ehsan Rahnamayan, Shahryar Miyandoab, Sevil Zanjani Bidgoli, Azam Asilian Tizhoosh, H.R. Lab Department of Electrical Computer and Software Engineering Ontario Tech University OshawaON Canada Department of Engineering Brock University St. CatharinesON Canada Faculty of Science Wilfrid Laurier University WaterlooON Canada Rhazes Lab Department of Artificial Intelligence and Informatics Mayo Clinic RochesterMN United States

Training Artificial Neural Networks (ANNs) poses a challenging and critical problem in machine learning. Despite the effectiveness of gradient-based learning methods, such as Stochastic Gradient Descent (SGD), in training neural networks, they do have several limitations. For instance, they require differentiable activation functions, and cannot optimize a model based on several independent non-differentiable loss functions simultaneously;for example, the F1-score, which is used during testing, can be used during training when a gradient-free optimization algorithm is utilized. Furthermore, the training (i.e., optimization of weights) in any DNN can be possible with a small size of the training dataset. To address these concerns, we propose an efficient version of the gradient-free Coordinate Search (CS) algorithm, an instance of General Pattern Search (GPS) methods, for training (i.e., optimizing) neural networks. The proposed algorithm can be used with non-differentiable activation functions and tailored to multi-objective/multi-loss problems. Finding the optimal values for weights of ANNs is a large-scale optimization problem. Therefore, instead of finding the optimal value for each variable, which is the common technique in classical CS, we accelerate optimization and convergence by bundling the variables (i.e., weights). In fact, this strategy is a form of dimension reduction for optimization problems. Based on the experimental results, the proposed method is comparable with the SGD algorithm, and in some cases, it outperforms the gradient-based approach. Particularly, in situations with insufficient labeled training data, the proposed CS method performs better. The performance plots demonstrate a high convergence rate, highlighting the capability of our suggested method to find a reasonable solution with fewer function calls. As of now, the only practical and efficient way of training ANNs with hundreds of thousands of weights is gradient-based algorithms such

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

MASKED DISTILLATION WITH RECEPTIVE TOKENS

arXiv

引用

arXiv 2022年

作者： Huang, Tao Zhang, Yuan You, Shan Wang, Fei Qian, Chen Cao, Jian Xu, Chang School of Computer Science Faculty of Engineering The University of Sydney Australia SenseTime Research Hong Kong School of Software and Microelectronics Peking University China University of Science and Technology of China China

Distilling from the feature maps can be fairly effective for dense prediction tasks since both the feature discriminability and localization priors can be well transferred. However, not every pixel contributes equally to the performance, and a good student should learn from what really matters to the teacher. In this paper, we introduce a learnable embedding dubbed receptive token to localize those pixels of interests (PoIs) in the feature map, with a distillation mask generated via pixel-wise attention. Then the distillation will be performed on the mask via pixel-wise reconstruction. In this way, a distillation mask actually indicates a pattern of pixel dependencies within feature maps of teacher. We thus adopt multiple receptive tokens to investigate more sophisticated and informative pixel dependencies to further enhance the distillation. To obtain a group of masks, the receptive tokens are learned via the regular task loss but with teacher fixed, and we also leverage a Dice loss to enrich the diversity of learned masks. Our method dubbed MasKD is simple and practical, and needs no priors of tasks in application. Experiments show that our MasKD can achieve state-of-the-art performance consistently on object detection and semantic segmentation benchmarks. Code is available at https://***/hunto/MasKD. © 2022, CC BY.

关键词： Distillation

来源：评论

学校读者我要写书评

暂无评论

Language-Conditioned Affordance-Pose Detection in 3D Point Clouds

arXiv

引用

arXiv 2023年

作者： Nguyen, Toan Vu, Minh Nhat Huang, Baoru Van Vo, Tuan Truong, Vy Le, Ngan Vo, Thieu Le, Bac Nguyen, Anh FPT Software AI Center Viet Nam Automation & Control Institute TU Wien Vienna Austria Imperial College London United Kingdom Department of Computer Science & Computer Engineering University of Arkansas United States Faculty of Mathematics and Statistics Ton Duc Thang University Ho Chi Minh City Viet Nam Department of Computer Science University of Science Viet Nam Department of Computer Science University of Liverpool United Kingdom

Affordance detection and pose estimation are of great importance in many robotic applications. Their combination helps the robot gain an enhanced manipulation capability, in which the generated pose can facilitate the corresponding affordance task. Previous methods for affodance-pose joint learning are limited to a predefined set of affordances, thus limiting the adaptability of robots in real-world environments. In this paper, we propose a new method for language-conditioned affordance-pose joint learning in 3D point clouds. Given a 3D point cloud object, our method detects the affordance region and generates appropriate 6-DoF poses for any unconstrained affordance label. Our method consists of an open-vocabulary affordance detection branch and a language-guided diffusion model that generates 6-DoF poses based on the affordance text. We also introduce a new high-quality dataset for the task of language-driven affordance-pose joint learning. Intensive experimental results demonstrate that our proposed method works effectively on a wide range of open-vocabulary affordances and outperforms other baselines by a large margin. In addition, we illustrate the usefulness of our method in real-world robotic applications. Our code and dataset are publicly available at https://***. © 2023, CC BY-NC-SA.

关键词： Robotics

来源：评论

学校读者我要写书评

暂无评论

Membership-Mappings for Practical Secure Distributed Deep Learning

arXiv

引用

arXiv 2022年

作者： Kumar, Mohit Zhang, Weiping Fischer, Lukas Freudenthaler, Bernhard The Software Competence Center Hagenberg Austria The Faculty of Computer Science and Electrical Engineering University of Rostock Germany The Northwestern Polytechnical University Suzhouzhong Road Suzhou China

This study leverages the data representation capability of fuzzy based membership-mappings for practical secure distributed deep learning using fully homomorphic encryption. The impracticality issue of secure machine (deep) learning with fully homomorphic encrypted data, arising from large computational overhead, is addressed via applying fuzzy attributes. Fuzzy attributes are induced by globally convergent and robust variational membership-mappings based local deep models. Fuzzy attributes combine the local deep models in a robust and flexible manner such that the global model can be evaluated homomorphically in an efficient manner using a boolean circuit composed of bootstrapped binary gates. The proposed method, while preserving privacy in a distributed learning scenario, remains accurate, practical, and scalable. The method is evaluated through numerous experiments including demonstrations through MNIST dataset and Freiburg Groceries Dataset. Further, a biomedical application related to mental stress detection on individuals is considered. © 2022, CC BY.

关键词： Mapping

来源：评论

学校读者我要写书评

暂无评论

Avast-CTU Public CAPE Dataset

arXiv

引用

arXiv 2022年

作者： Bošanský, Branislav Kouba, Dominik Maňhal, Ondřej Sick, Thorsten Lisý, Viliam Křoustek, Jakub Somol, Petr Avast Software Czech Republic Artificial Intelligence Center Dept. of Computer Science Faculty of Electrical Engineering Czech Tecnical University in Prague Czech Republic

There is a limited amount of publicly available data to support research in malware analysis technology. Particularly, there are virtually no publicly available datasets generated from rich sandboxes such as Cuckoo/CAPE. The benefit of using dynamic sandboxes is the realistic simulation of file execution in the target machine and obtaining a log of such execution. The machine can be infected by malware hence there is a good chance of capturing the malicious behavior in the execution logs, thus allowing researchers to study such behavior in detail. Although the subsequent analysis of log information is extensively covered in industrial cybersecurity backends, to our knowledge there has been only limited effort invested in academia to advance such log analysis capabilities using cutting edge techniques. We make this sample dataset available to support designing new machine learning methods for malware detection, especially for automatic detection of generic malicious behavior. The dataset has been collected in cooperation between Avast software and Czech Technical University - AI Center (AIC). Copyright © 2022, The Authors. All rights reserved.

关键词： Malware

来源：评论

学校读者我要写书评

暂无评论

A High-Resolution Approach for Dynamic Traffic Police Gestures Recognition Based on Spatial Context and Temporal Features Fusion

A High-Resolution Approach for Dynamic Traffic Police Gestur...

引用

International Conference on Image, Vision and Computing (ICIVC)

作者： Jian He Shengsheng Jiang Xin Wei Cheng Zhang Ruihai Dong Beijing Engineering Research Center for IOT Software and Systems Beijing University of Technology Beijing China Faculty of Information Technology Beijing University of Technology Beijing China School of Computer Science University College Dublin Dublin Ireland

According to the requirement of recognizing traffic police gestures for driver assistance systems and intelligent vehicles, a universal model for dynamic traffic police gesture recognition is firstly introduced, of which can accurately present the spatial context (such as the relative lengths of skeletons, the angles between each skeleton w. r. t. gravity, and part features) of the traffic police gestures. Secondly, an architecture which can respectively extract spatial context and temporal features of dynamic traffic police gesture is proposed. Meanwhile, deep neural network and LSTM are introduced to build a high-resolution traffic police gestures recognizer (namely HRTPGR). At last, the open Police Gesture Dataset is used to train and test TPGR, and the experimental results show that the TPGR achieves a state-of-the-art accuracy with 98.7% for dynamic traffic police gestures recognition, and has strong anti-interference ability to light, background and gesture shape changes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Multi-Swarm Genetic Gray Wolf Optimizer with Embedded Autoencoders for High-Dimensional Expensive Problems

SSRN

引用

SSRN 2023年

作者： Zhai, Jiahui Bi, Jing Yuan, Haitao Zhou, Mengchu School of Software Engineering Faculty of Information Technology Beijing University of Technology Beijing100124 China School of Automation Science and Electrical Engineering Beihang University Beijing100191 China Department of Electrical and Computer Engineering New Jersey Institute of Technology NewarkNJ07102 United States

High-dimensional expensive problems are often encountered in the design and optimization of complex robotic and automated systems and distributed computing systems, and they suffer from a time-consuming fitness evaluation process. It is extremely challenging and difficult to produce promising solutions in high-dimensional search space. This work proposes an evolutionary optimization framework with embedded autoencoders that effectively solve optimization problems with high-dimensional search spaces. Autoencoders provide strong dimension reduction and feature extraction abilities that compress a high-dimensional space to an informative low-dimensional one. Search operations are performed in a low-dimensional space, thereby guiding a whole population to converge to the optimal solution more efficiently. Multiple subpopulations coevolve iteratively in a distributed manner. One subpopulation is embedded by an autoencoder, and the other one is guided by a proposed Multi-swarm Gray wolf optimizer based on Genetic learning (MGG). Thus, the proposed multi-swarm framework is named Autoencoder-based MGG (AMGG). AMGG consists of three proposed strategies that well balance exploration and exploitation abilities, i.e., a Dynamic subgroup Number Strategy for reducing the number of subpopulations, a Subpopulation Reorganization Strategy for sharing useful information about each subpopulation, and a Purposeful Detection Strategy for jumping out of local optima and improving exploration ability. AMGG is compared with several widely used algorithms by using typical benchmark functions and a real-life optimization problem. Extensive experimental results prove that AMGG outperforms its peers in terms of search accuracy and convergence efficiency. © 2023, The Authors. All rights reserved.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Sovereign Allocation of Resources in Cloud Milieus Using a Causal Dilated Geometric Algebra Approach for Dynamic Scalability 2

Enhancing Sovereign Allocation of Resources in Cloud Milieus...

引用

2nd International Conference on Machine Learning and Autonomous Systems, ICMLAS 2025

作者： Katru, Chandrasekhar Rao Srinivasan, Sathish Kumar, Mohan Yadwad, Sunita Satish, G. Maranan, Ramya Lead Software Engineer Indian LandSC29707 United States Machine Learning & AI Development Oracle Cloud Infrastructure Division San FranciscoCA United States Nitte Meenakshi Institute of Technology Department of Information Science and Engineering Karnataka Bengaluru India Parul institute of Engineering and Technology Parul University Computer science and Engineering Faculty of Engineering and Technology Gujarat India Sree Dattha Institute of Engineering and Science Department of Electrical and Electronics Engineering Telangana Sheriguda India Saveetha School of Engineering SIMATS Department of Research and Innovation Tamil Nadu Chennai India

ISBN: (纸本)9798331505745

Cloud environments utilize availability and usage of resources as crucial components in order to produce scalability, reliability and low cost. Such resource capabilities require autonomous systems that can handle these resources dynamically in spite of fluctuating workloads and service delivery requirements. Static models of resource management suffer from scalability and inability to react on the fly and accurately predict the demand thus causing Service Level Agreement (SLA) breaches and affecting the Quality of Service (QoS) as well as energy consumption profile. Advanced and elaborative cloud workloads require an intelligent system that can analyse the temporal and spatial patterns without impacting the overall system's performance significantly. Inspired by these challenges, this research proposes a Causal Dilated Geometric Algebra Convolutional Transformer Network (CATNet) along with the Prairie-Dog Optimizer (P-DogO), referred to as CAT-DogNet to learn and predict the dynamic scalability. CATNet integrates Causal Dilated Convolutional Networks in time domain for temporal structure capturing and Geometric Algebra Transformer for spatial resource coding. P-DogO adjusts weight parameters and losses for resource allocation, enhancing them depending on a work environment. A set of comprehensive assessments demonstrate a 0.85% SLA violation rate, average response time of less than 10ms, and overall 12.3% less energy consumption than baseline methods. The system had favourable predictability rates over 99.4% for the resource demand estimate. CAT-DogN et presents a sound and agnostic architecture for autonomous resource allocation in cloud environment, which indeed extend the state of art by considering flexibility, power consumption and QoS compliance. © 2025 IEEE.

关键词： Infrastructure as a service (IaaS)

来源：评论

学校读者我要写书评

暂无评论

Efficient Server-Aided Personalized Treatment Recommendation with Privacy Preservation

Efficient Server-Aided Personalized Treatment Recommendation...

引用

GLOBECOM 2022 - 2022 IEEE Global Communications Conference

作者： Dan Zhu Hui Zhu Cheng Huang Rongxing Lu Xuemin Shen Dengguo Feng Department of Cyber Engineering Xidian University Xi'an China Department of Electrical and Computer Engineering University of Waterloo Waterloo Canada Faculty of Computer Science University of New Brunswick Fredericton Canada State Key Laboratory of Computer Science Institute of Software Chinese Academy of Sciences Beijing China

ISBN: (纸本)9781665435413

With AI-derived knowledge graph (KG), medical centers can recommend appropriate treatment options to physicians as references based on their patients' personal healthcare information (PHI). However, the treatment recommendation services may also cause serious privacy concerns. In this paper, we propose an efficient and privacy-preserving personalized treatment recommendation scheme with the aid of a third-party server. Specifically, a medical center denotes the KG of each disease by a directed graph with conditional edges and vertices that describe the treatment options and costs in different states. To prevent privacy leakage while reducing computational and management cost, the graphs are encrypted and then delegated to an honest-but-curious server. With the assistance of the server, physicians can set proper illness states and cost requirements according to patients' PHI, and correspondingly generate personalized ciphertexts to retrieve appropriate treatment options. The key component of the proposed scheme is a novel designed secure and flexible path comparison protocol, by tailoring a symmetric homomorphic encryption algorithm and combining it with a secure hash function. The protocol can enable the server to compare the uploaded ciphertexts with encrypted graphs in a secure and efficient way. Comprehensive security analysis indicates that the proposed scheme can meet desirable privacy requirements, and extensive experimental results demonstrate its practicality.

关键词： Hash functions Privacy Protocols Costs Medical services Servers Cryptography

来源：评论

学校读者我要写书评

暂无评论

Effects of term weighting approach with and without stop words removing on Arabic text classification

Effects of term weighting approach with and without stop wor...

引用

International Conference on Optimization and Applications (ICOA)

作者： Esra’a Alhenawi Ruba Abu Khurma Pedro A. Castillo Maribel G. Arenas Ayat Mahmoud Al-Hinawi Department of Software Engineering Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Computer Science MEU Research Unit Faculty of Information Technology Middle East University Amman Jordan University of Granada Granada Spain Department of Allied Engineering Sciences Hashemite University Zarqa Jordan

Text classification is a technique for grouping articles into pre-defined categories. Prior to categorization, text documents have to be set up and organised in a form that is compatible with the data mining techniques. That has produced many term weighting techniques have been developed in the literature to improve the functionality of text categorization systems. This paper compares techniques for text classification based on when stop words are eliminated from the documents once and when they are not. We used an Arabic data set of 322 papers grouped into six subjects (health, politics, science, education, agriculture and finance) to research which is the influence of prior weighting of features approaches on classification outcomes with regard to accuracy, recall, precision, and F-measure values. Each document subset includes 50 documents, except the health one that includes 61. We carried out four experiments and checked results getting that only for precision, the term frequency feature weighting approach with stop word removal are more or less the same than for binary method. Moreover the conclusion for accuracy, recall and F-measure is that Feature weighting approach with stop word outperforms the Binary one. Additionally, if the phrase for weighting is the same for both methods, to remove stop word increases classification accuracy for all the experiments.

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：