检索结果-内蒙古大学图书馆

Bridging the Artificial Intelligence Knowledge and Skill Gaps in Africa: a Case of the 3rd Google Tensorflow Bootcamp and FEDGEN Mini-Workshop

学校读者我要写书评

暂无评论

Bridging the Artificial Intelligence Knowledge and Skill Gap...

Science, engineering and Business for Sustainable Development Goals (SEB-SDG), International Conference on

作者： Emmanuel Adetiba John S. Wejin Oluwadamilola Oshin Ayodele H. Ifijeh Comfort Lawal Surendra Colin Thakur Ayokunle A. Awelewa Raymond Jules Kala Priscilla O. Ajayi Matthew B. Akanle Faith O. Sweetwiliams Uche Nnaji Emmanuel Owolabi Olabode Idowu-Bismark Gabriel Sobola Department of Electrical and Information Engineering & Covenant Applied Informatics & Communication African Center of Excellene (CApIC-ACE) Covenant University Ota Nigeria HRA Institute for Systems Science Durban University of Technology Durban South Africa Department of Electrical and Information Engineering & CApIC-ACE Covenant University Jalingo Nigeria Department of Computer Science Taraba State University Jalingo Nigeria Department of Electrical and Information Engineering & CApIC-ACE Covenant University Ota Nigeria Department of Information Technology and KZN E-Skills Co-Laboratory Durban University of Technology Durban South Africa Department of Electrical and Information Engineering Covenant University Ota Nigeria International University of Grand Bassam Grand Bassam Ivory Coast Center for Systems and Information Services & CApIC-ACE Covenant University Ota Nigeria Department of Computer and Information Science & CApIC-ACE Covenant University Ota Nigeria Smartyou Integral (PTY) LTD Pretoria Gauteng South Africa

ISBN: (数字)9798350358155

ISBN: (纸本)9798350358162

In transiting from one civilization to another, technology has played a vital and positive role. In the 21 st century, one of the digital developments that is paving ways for human life improvement is machine-assisted technology using Artificial Intelligence (AI). Artificial Intelligence has successfully enhanced man’s capacity in solving complex problems and processes. However, as developed nations continue to reap from the adoption of AI in various fields of human endeavors, the continent of Africa has remained behind, especially in AI-based skills and research. Various governments in developing nations have encouraged the adoption of AI, especially in institutions of learning. However, theoretical adoption without practical experience has remained an ineffective way of bridging the digital divide. In this paper we present the outcome of a practical approach to bridging the AI divide among students and researchers in Africa through funding support from the Google TensorFlow College Outreach Award. A 3-day hybrid bootcamp was organized (11 th to 13 th December, 2023) using the Google funding in order to equip postgraduate students and researchers with AI and collaborative research skills. A pre-survey method was employed to ascertain the knowledge level of the bootcamp participants. From the pre-surveyed feedback, training sessions on various AI domains were presented, and participant equipped with practical AI skills using a deployed AI-based cloud programming platform running on the private Federated Genomic Cloud (FEDGEN) infrastructure at Covenant University. A post-survey feedback was used to ascertain the effectiveness of this approach. A comparative analysis of the pre-survey and post-survey reveals a 70% improvement of AI skills among participants. This shows that having continuous training session for students and researchers is an effective method in closing the AI skills gap between developed and developing nations.

关键词： Training Surveys Knowledge based systems Government Genomics Africa Programming

Improving Generalization of Metric Learning via Listwise Self-distillation

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zeng, Zelong Yang, Fan Wang, Zheng Satoh, Shin'ichi The Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Japan The Digital Content and Media Sciences Research Division National Institute of Informatics Japan The School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University China

Most deep metric learning (DML) methods employ a strategy that forces all positive samples to be close in the embedding space while keeping them away from negative ones. However, such a strategy ignores the internal relationships of positive (negative) samples and often leads to overfitting, especially in the presence of hard samples and mislabeled samples. In this work, we propose a simple yet effective regularization, namely Listwise Self-Distillation (LSD), which progressively distills a model's own knowledge to adaptively assign a more appropriate distance target to each sample pair in a batch. LSD encourages smoother embeddings and information mining within positive (negative) samples as a way to mitigate overfitting and thus improve generalization. Our LSD can be directly integrated into general DML frameworks. Extensive experiments show that LSD consistently boosts the performance of various metric learning methods on multiple datasets. Copyright © 2022, The Authors. All rights reserved.

关键词： Distillation

A Study of Multilayer Omega Networks Operating with Cut-Through Mechanism under Uniform Traffic

学校读者我要写书评

暂无评论

A Study of Multilayer Omega Networks Operating with Cut-Thro...

South Eastern European Design Automation, computer engineering, computer Networks and Social Media Conference (SEEDA-CECNSM)

作者： Eleftherios Stergiou John Garofalakis Dimitrios Liarokapis Spiridoula V. Margariti Dept. Informatics & Telecommunications University of Ioannina Arta Greece Dept. of Computer Engineering and Informatics University of Patras and Computer Technology Institute and Press—“DIOPHANTUS” (CTI)) Patras Greece

ISBN: (数字)9781728164458

ISBN: (纸本)9781728164465

There is an enduring interest in developing more efficient multistage interconnection networks (MINs), as they are a key aspect of various switching sectors and the demands for higher data transfer rates. Here, semi-layer Omega type networks operating under the cut-through forwarding policy are selected as a test-bed subject for performance evaluation. This special shuffle-exchange network was modelled, analysed, and simulated. Moreover, this type of fabric is compared with corresponding single-layer Omega networks operating via cut-through or a `store and forward' forwarding technique. The results show, in a quantitative manner, how superior is the under study fabric compared to the corresponding single-layer constructions, in terms of network size, showing the advantages that are provided by both usages: fan-out and cut-through mechanisms. Moreover, the roles of the switch element's size and the reliability metric were investigated. The findings that are derived can be valuable assets for MIN designers, in order to achieve more efficient delivering networks with low overall deployment costs.

关键词： Omega network banyan networks performance evaluation cut-through semi-layer multistage interconnection networks uniform traffic multistage interconnection networks cut-through Performance Evaluation Materials

Automated Dominative Subspace Mining for Efficient Neural Architecture Search

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Chen, Yaofo Guo, Yong Liao, Daihai Lv, Fanbing Song, Hengjie Kwok, James Tin-Yau Tan, Mingkui School of Software Engineering South China University of Technology Guangzhou510641 China Max Planck Institute for Informatics Max Planck Institute Saarbrücken66123 Germany Changsha Hisense Intelligent System Research Institute Co. Ltd Changsha410006 China Department of Computer Science and Engineering The Hong Kong University of Science and Technology 999077 Hong Kong

Neural Architecture Search (NAS) aims to automatically find effective architectures within a predefined search space. However, the search space is often extremely large. As a result, directly searching in such a large search space is non-trivial and also very time-consuming. To address the above issues, in each search step, we seek to limit the search space to a small but effective subspace to boost both the search performance and search efficiency. To this end, we propose a novel Neural Architecture Search method via Dominative Subspace Mining (DSM-NAS) that finds promising architectures in automatically mined subspaces. Specifically, we first perform a global search, i.e., dominative subspace mining, to find a good subspace from a set of candidates. Then, we perform a local search within the mined subspace to find effective architectures. More critically, we further boost search performance by taking well-designed/searched architectures to initialize candidate subspaces. Experimental results demonstrate that DSM-NAS not only reduces the search cost but also discovers better architectures than state-of-the-art methods in various benchmark search spaces. Copyright © 2022, The Authors. All rights reserved.

关键词： Local search (optimization)

IBICA 2023 Preface – Volume 4

学校读者我要写书评

暂无评论

Lecture Notes in Networks and Systems

Lecture Notes in Networks and Systems 2025年 1231 LNNS卷 v-vi页

作者： Sakalauskas, Virgilijus Perumal, Thinakaran Abraham, Ajith Thekkath, Preethi Kriksciuniene, Dalia Sun, Yunchuan Kamimura, Ryotaro Sreedhar, Sreela Bajaj, Anu Department of Informatics Vilnius University Vilnius Lithuania School of Artificial Intelligence Sai University Chennai India Department of Computer Science and Engineering Thapar Institute of Engineering and Technology Punjab Patiala India

Geo-Localization via Ground-to-Satellite Cross-View Image Retrieval

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Zeng, Zelong Wang, Zheng Yang, Fan Satoh, Shin'ichi The School of Computer Science National Engineering Research Center for Multimedia Software Wuhan University China The Department of Information and Communication Engineering Graduate School of Information Science and Technology The University of Tokyo Japan The Digital Content and Media Sciences Research Division National Institute of Informatics Japan

The large variation of viewpoint and irrelevant content around the target always hinder accurate image retrieval and its subsequent tasks. In this paper, we investigate an extremely challenging task: given a ground-view image of a landmark, we aim to achieve cross-view geo-localization by searching out its corresponding satellite-view images. Specifically, the challenge comes from the gap between ground-view and satellite-view, which includes not only large viewpoint changes (some parts of the landmark may be invisible from front view to top view) but also highly irrelevant background (the target landmark tend to be hidden in other surrounding buildings), making it difficult to learn a common representation or a suitable mapping. To address this issue, we take advantage of drone-view information as a bridge between ground-view and satellite-view domains. We propose a Peer Learning and Cross Diffusion (PLCD) framework. PLCD consists of three parts: 1) a peer learning across ground-view and drone-view to find visible parts to benefit ground-drone cross-view representation learning;2) a patch-based network for satellite-drone cross-view representation learning;3) a cross diffusion between ground-drone space and satellite-drone space. Extensive experiments conducted on the University-Earth and University-Google datasets show that our method outperforms state-of-the-arts significantly. Copyright © 2022, The Authors. All rights reserved.

关键词： Satellites

Simres-TV: Noise and residual similarity for parameter estimation in total variation 4

学校读者我要写书评

暂无评论

Simres-TV: Noise and residual similarity for parameter estim...

4th International Workshop on Photogrammetric and computer Vision Techniques for Video Surveillance, Biometrics and Biomedicine, PSBB 2021

作者： Prasath, V.B. Surya Hien, Nguyen Ngoc Thanh, Dang N.H. Dvoenko, Sergey Division of Biomedical Informatics Cincinnati Children's Hospital Medical Center CincinnatiOH45229 United States Department of Pediatrics University of Cincinnati College of Medicine CincinnatiOH45257 United States Department of Biomedical Informatics College of Medicine University of Cincinnati OH45267 United States Department of Electrical Engineering and Computer Science University of Cincinnati OH45221 United States Dong Thap University Cao Lanh City Viet Nam Department of Information Technology School of Business Information Technology University of Economics Ho Chi Minh City Viet Nam Institute of Applied Mathematics and Computer Science Tula State University Russia

Image restoration with regularization models is very popular in the image processing literature. Total variation (TV) is one of the important edge preserving regularization models used, however, to obtain optimal restoration results the regularization parameter needs to be set appropriately. We propose here a new parameter estimation approach for total variation based image restoration. By utilizing known noise levels we compute the regularization parameter by reducing the similarity between residual and noise variances. We use the split Bregman algorithm for the total variation along with this automatic parameter estimation step to obtain a very fast restoration scheme. Experimental results indicate the proposed parameter estimation obtained better denoised images and videos in terms of PSNR and SSIM measures and the computational overload is less compared with other approaches. © Authors 2021. CC BY 4.0 License.

关键词： Image reconstruction

Machine Learning and computer Vision Techniques in Continuous Beehive Monitoring Applications: A Survey

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Bilik, Simon Zemcik, Tomas Kratochvila, Lukas Ricanek, Dominik Richter, Miloslav Zambanini, Sebastian Horak, Karel Department of Control and Instrumentation Faculty of Electrical Engineering and Communication Brno University of Technology Technická 3058/10 Brno61600 Czech Republic Computer Vision and Pattern Recognition Laboratory Department of Computational Engineering Lappeenranta-Lahti University of Technology LUT Yliopistonkatu 34 Lappeenranta53850 Finland Computer Vision Lab Institute of Visual Computing & Human-Centered Technology Faculty of Informatics TU Wien Favoritenstr. 9/193-1 ViennaA-1040 Austria

Wide use and availability of machine learning and computer vision techniques allows development of relatively complex monitoring systems in many domains. Besides the traditional industrial domain, new applications appears also in biology and agriculture, where they may be used to detect infections, parasites and weeds, but also for automated monitoring and early warning systems. This goes in concordance with the introduction of the easily accessible hardware and development kits such as the Arduino, or RaspberryPi families. In this paper, we survey 50 papers focusing on the methods of automated beehive monitoring using computer vision techniques. Particularly on the pollen and Varroa mite detection together with the bee traffic monitoring. Such systems could also be used for monitoring of honeybee colonies and for the inspection of their health state, which could potentially identify dangerous states before the situation is critical, or to better plan periodic bee colony inspections and therefore save significant costs. Further on, we also include analysis of the research trends in this application field and we outline the possible directions of new development. Our paper is also aimed at veterinary and apidology professionals and experts, who may not be familiar with machine learning to introduce them to its capabilities, hence each family of techniques is prefaced by a brief theoretical introduction and motivation related to its base method. We hope that this paper will inspire other scientists to use machine learning techniques for other applications in beehive monitoring. © 2022, CC BY.

关键词： computer vision

The Development of the Multi-Layer Security Network Authentication System using Blockchain technology

学校读者我要写书评

暂无评论

The Development of the Multi-Layer Security Network Authenti...

International Conference on System Modeling & Advancement in Research Trends (SMART)

作者： S. K. UmaMaheswaran Arti Rana Kavita Rani Yashpal Singh Suhas Harbola Kumud Pant Department of Mathematics Sri Sai Ram Engineering College Chennai Tamil Nadu India Uttaranchal Institute of Technology Uttaranchal University Department of CSE Lloyd Institute of Engineering and Technology Greater Noida Uttar Pradesh Department of Computer Science & Engineering Jain (Deemed-to-be University) Bengaluru Karnataka India National Informatics Centre (NIC) New Delhi Delhi India Department of Biotechnology Graphic Era Deemed to be University Dehradun Uttarakhand India

ISBN: (纸本)9781665487351

Due to the fact that crypto is a novel security strategy. This section outlines a multi-layer safe Internet of Everything networks theory based on blockchains, we will now explain the construction of a layered network security authenticator using blockchain technologies. By grouping Connected technologies into a pass connectivity and implementing the blockchain based platform at every level of a network, the strategy reduces the challenges of actually deploying blockchain technologies while maintaining the mankind's strict security and validity guarantee. It offers a nationwide connectivity option for the Web of Things. A stone chain is a collection of blocks that holds data. The kind of public blockchain affects the information stored inside a piece. For instance, a lot coin block contains data about the Presenter, the Reception, and the amount of bit coins that will be communicated. The brand's first block is called the Node. The goal of the block chain is to make data available to everyone who uses a program to access it. Entry to all this account for reading may be unrestricted (‘permit less’) or restricted (‘approval’). Block chain today makes it feasible to send, receive, and store digital data in a secure manner. Additionally, it uses mathematical encryption to protect every transaction. By adopting this, banks might boost their current security and disclosures to unprecedented heights.

关键词： Authorization Steganography Privacy Authentication Quality control Blockchains Encryption