检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Marks, Markus Knott, Manuel Kondapaneni, Neehar Cole, Elijah Defraeye, Thijs Perez-Cruz, Fernando Perona, Pietro California Institute of Technology United States ETH Zurich Institute for Machine Learning Department of Computer Science Switzerland Swiss Data Science Center ETH Zurich and EPFL Switzerland Empa Swiss Federal Laboratories for Materials Science and Technology Switzerland Altos Labs Switzerland

Self-supervised learning (SSL) is a machine learning approach where the data itself provides supervision, eliminating the need for external labels. The model is forced to learn about the data's inherent structure or context by solving a pretext task. With SSL, models can learn from abundant and cheap unlabeled data, significantly reducing the cost of training models where labels are expensive or inaccessible. In computer Vision, SSL is widely used as pre-training followed by a downstream task, such as supervised transfer, few-shot learning on smaller labeled data sets, and/or unsupervised clustering. Unfortunately, it is infeasible to evaluate SSL methods on all possible downstream tasks and objectively measure the quality of the learned representation. Instead, SSL methods are evaluated using in-domain evaluation protocols, such as fine-tuning, linear probing, and k-nearest neighbors (kNN). However, it is not well understood how well these evaluation protocols estimate the representation quality of a pre-trained model for different downstream tasks under different conditions, such as dataset, metric, and model architecture. In this work, we study how classification-based evaluation protocols for SSL correlate and how well they predict downstream performance on different dataset types. Our study includes eleven common image datasets and 26 models that were pre-trained with different SSL methods or have different model backbones. We find that in-domain linear/kNN probing protocols are, on average, the best general predictors for out-of-domain performance. We further investigate the importance of batch normalization for the various protocols and evaluate how robust correlations are for different kinds of dataset domain shifts. In addition, we challenge assumptions about the relationship between discriminative and generative self-supervised methods, finding that most of their performance differences can be explained by changes to model backbones. Copyright © 2024, The

关键词： Nearest neighbor search

来源：评论

学校读者我要写书评

暂无评论

Machine learning of noise-resilient quantum circuits

arXiv

引用

arXiv 2020年

作者： Cincio, Lukasz Rudinger, Kenneth Sarovar, Mohan Coles, Patrick J. Theoretical Division MS 213 Los Alamos National Laboratory Los AlamosNM87545 United States Quantum Computer Science Sandia National Laboratories AlbuquerqueNM87185 United States Extreme-Scale Data Science and Analytics Sandia National Laboratories LivermoreCA94550 United States

Noise mitigation and reduction will be crucial for obtaining useful answers from near-term quantum computers. In this work, we present a general framework based on machine learning for reducing the impact of quantum hardware noise on quantum circuits. Our method, called noise-aware circuit learning (NACL), applies to circuits designed to compute a unitary transformation, prepare a set of quantum states, or estimate an observable of a many-qubit state. Given a task and a device model that captures information about the noise and connectivity of qubits in a device, NACL outputs an optimized circuit to accomplish this task in the presence of noise. It does so by minimizing a task-specific cost function over circuit depths and circuit structures. To demonstrate NACL, we construct circuits resilient to a fine-grained noise model derived from gate set tomography on a superconducting-circuit quantum device, for applications including quantum state overlap, quantum Fourier transform, and W-state preparation. Copyright © 2020, The Authors. All rights reserved.

关键词： Qubits

来源：评论

学校读者我要写书评

暂无评论

Facilitated machine learning for image-based fruit quality assessment

arXiv

引用

arXiv 2022年

作者： Knott, Manuel Perez-Cruz, Fernando Defraeye, Thijs Empa Swiss Federal Laboratories for Materials Science Technology Laboratory for Biomimetic Membranes and Textiles St. Gallen Switzerland Swiss Data Science Center ETH Zurich and EPFL Zurich Switzerland Institute for Machine Learning Department of Computer Science ETH Zurich Switzerland

Image-based machine learning models can be used to make the sorting and grading of agricultural products more efficient. In many regions, implementing such systems can be difficult due to the lack of centralization and automation of postharvest supply chains. Stakeholders are often too small to specialize in machine learning, and large training data sets are unavailable. We propose a machine learning procedure for images based on pre-trained Vision Transformers. It is easier to implement than the current standard approach of training Convolutional Neural Networks (CNNs) as we do not (re-)train deep neural networks. We evaluate our approach based on two data sets for apple defect detection and banana ripeness estimation. Our model achieves a competitive classification accuracy equal to or less than one percent below the best-performing CNN. At the same time, it requires three times fewer training samples to achieve a 90% accuracy. © 2022, CC BY.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

A Proposal to Find Mutually Contributable Business or Life Activities Using Conformance Checking

引用

Procedia computer science 2022年 207卷 542-551页

作者： Haruhiko Kaiya Tomoya Misawa Shinpei Ogata Shinobu Saito Hiroyuki Nakagawa Hironori Takeuchi Kanagawa University Hiratsuka 259-1293 Japan Shinshu University Nagano 380-8553 Japan NTT Computer and Data Science Laboratories Tokyo 108-0023 Japan Osaka University Suita 565-0871 Japan Musashi University Tokyo 176-8534 Japan

We propose a method to comprehensively find a pair of business or life activities, which can mutually contribute to each other. We assume that the activities with synchronized processes can mutually contribute to each other. A process model of an activity is thus compared to a log of another activity for measuring whether the activities can synchronize their processes to a certain extent using a conformance checking technique. The threshold of the extent is defined on the basis of a randomly generated log containing the same events as those in the compared log. We tentatively evaluated the method through a case study, and confirmed that the method seemed to be valid.

关键词： Cross-organizational process Sharing process Process mining Conformance checking

来源：评论

学校读者我要写书评

暂无评论

End-to-end statistical delay service under GPS and EDF scheduling: a comparison study

End-to-end statistical delay service under GPS and EDF sched...

引用

IEEE Annual Joint Conference: INFOCOM, IEEE computer and Communications Societies

作者： V. Sivaraman F.M. Chiussi M. Gerla Atoga Systems Fremont CA USA Data Networking Research Bell Laboratories Lucent Technologies Inc. Holmdel NJ USA Department of Computer Science University of California Los Angeles CA USA

ISBN: (纸本)0780370163

Generalized processor sharing (GPS) has gained much popularity as a simple and effective scheduling mechanism for the provisioning of quality of service (QoS) in emerging high-speed networks. For supporting deterministic end-to-end delay guarantees, GPS is known to be sub-optimal in comparison to the earliest deadline first (EDF) scheduling discipline; nevertheless it is often prefered over EDF due to its simplicity. In this paper, using analytical frameworks developed in the literature, we reassess the merits of GPS as compared to EDF in the setting of statistical delay service. Our contributions are threefold. The statistical frameworks in the literature enable the aggregate losses (i.e., delay bound violations) at an EDF scheduler to be estimated-our first contribution, therefore, is to develop a mechanism that allows the aggregate losses to translate to per-flow guarantees. This is achieved by means of a simple packet discard scheme that drops packets fairly then delay violations are imminent at the EDF scheduler. The discard mechanism has a constant complexity and is feasible for implementation in current packet switches. The ability to derive the per-flow guarantees from the aggregate allows a direct comparison between EDF and GPS-our next contribution, therefore, is to show for various traffic mixes with given per-flow loss constraints that EDF offers consistently larger schedulable regions than GPS, both in the single-hop and multi-hop setting. As our final contribution, we argue that the use of GPS for statistical delay support is inherently problematic. We demonstrate that achieving the maximal schedulable regions under GPS could necessitate dynamic resynchronization of the GPS weights, an operation considered infeasible for practical implementation.

关键词： Global Positioning System Processor scheduling Quality of service Optimal scheduling Aggregates Delay estimation Packet switching Switches computer science Drives

来源：评论

学校读者我要写书评

暂无评论

Optimal cavity design for minimizing errors in cavity-QED-based atom-photon entangling gates with finite temporal duration

arXiv

引用

arXiv 2022年

作者： Utsugi, Takeru Asaoka, Rui Tokunaga, Yuuki Aoki, Takao Department of Applied Physics Waseda University 3-4-1 Okubo Shinjuku-ku Tokyo169-8555 Japan Computer & Data Science Laboratories NTT Corporation Musashino Tokyo180-8585 Japan

We investigate atom-photon entangling gates based on cavity quantum electrodynamics (QED) for a finite photon-pulse duration, where not only the photon loss but also the temporal mode-mismatch of the photon pulse becomes a severe source of error. We analytically derive relations between cavity parameters, including transmittance, length, and effective cross-sectional area of the cavity, that minimize both the photon loss probability and the error rate due to temporal mode-mismatch by taking it into account as state-dependent pulse delay. We also investigate the effects of pulse distortion using numerical simulations for the case of short pulse duration. We believe that these analyses are the first to suggest that a cavity has an optimal length for the atom-photon gate, providing a fundamental guideline for implementing quantum information processing. Copyright © 2022, The Authors. All rights reserved.

关键词： Atoms

来源：评论

学校读者我要写书评

暂无评论

Improving Power Allocation and Installation in WSN Using Novel Nature-Inspired Optimization for Cyber Security Applications 1

Improving Power Allocation and Installation in WSN Using Nov...

引用

1st Asian Conference on Communication and Networks, ASIANComNet 2024

作者： Balamurugan, K.S. Kalyani, Gedela Al-Fatlawy, Ramy Kurdi, Waleed Hadi Madhloom Alsalamy, Fatima Al-Aboudy, H.M. Manikandan, K. Karpaga Vinayaga College of Engineering and Technology Department of ECE Tamil Nadu Chengalpattu India Karpaga Vinayaga College of Engineering and Technology Big Data Analytics Tamil Nadu Chengalpattu India The Islamic University College of Technical Engineering Department of Computer Technical Engineering Najaf Iraq Altoosi University College Department of Computer Science Najaf Iraq Al-Mustaqbal University Medical Laboratories Techniques Department Hillah Iraq Mazaya University College DhiQar Department of Computer Techniques Engineering Iraq Sona College of Technology Department of Biomedical Engineering Tamil Nadu Salem India

ISBN: (纸本)9798350367003

Wireless sensor network (WSN) installation and power allocation optimization for cybersecurity purposes are difficult tasks which include a well-thought-out method that strikes a balance between goals such as the energy efficiency, connectivity and cyber threat resistance while improving overall system performance and cybersecurity. A novel multi-task walrus optimization (MTWO) technique is offered in this study. The installation and power allocation problem (IPAP) with several jobs is established in this research. The suggested MTWO is used to split the IPAP into numerous scalar components, which are consequently grouped and treated by their desired goals. We evaluate the proposed MTWO approach using simulations and show that it works well in practice. The findings demonstrate that power distribution and installation for cybersecurity activities on WSNs can be improved by the MTWO. The superiority of the problem specific MTWO over the MOGA has been demonstrated by simulation outcome in several network cases, offering a wide range of excellent network designs to aid in the decision-maker selection. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

Basketball player’s value evaluation by a networks-based variant parameter hidden markov model

arXiv

引用

arXiv 2020年

作者： Du, Xin Cai, Weihong Liu, Jianquan Yu, Ding Xu, Kai Li, Wei Department of Computer Science College of Engineering Shantou University China Big Data Research Institute Tong Xing Technology Corporation China System Platform Research Laboratories NEC Corporation Japan Graduate School of Science and Engineering Hosei University Japan

Determining the value of basketball players through analyzing the players’ behavior is important for the managers of modern basketball teams. However, conventional methods always utilize isolated statistical data, leading to ineffective and inaccurate evaluations. Existing models based on dynamic network theory offer major improvements to the results of such evaluations, but said models remain imprecise because they focus merely on evaluating the values of individual players rather than considering them within their current teams. To solve this problem, we propose an analysis and evaluation model based on networks and a hidden Markov model. To the best of our knowledge, we are the first to combine a network form representing the players who are playing with the use of a hidden Markov model to mine the network and generate the desired results. Applying our approach to SportVU data collected from the National Basketball Association shows that this analysis and evaluation model can effectively analyze the performance of each player in a game and provides an assistive tool for team managers. Copyright © 2020, The Authors. All rights reserved.

关键词： Hidden Markov models

来源：评论

学校读者我要写书评

暂无评论

All in One: Multi-Task Prompting for Graph Neural Networks

arXiv

引用

arXiv 2023年

作者： Sun, Xiangguo Cheng, Hong Li, Jia Liu, Bo Guan, Jihong Department of Systems Engineering and Engineering Management Shun Hing Institute of Advanced Engineering The Chinese University of Hong Kong Hong Kong Data Science and Analytics Thrust The Hong Kong University of Science and Technology Guangzhou China School of Computer Science and Engineering Southeast University Purple Mountain Laboratories China Department of Computer Science and Technology Tongji University China

Recently, "pre-training and fine-tuning" has been adopted as a standard workflow for many graph tasks since it can take general graph knowledge to relieve the lack of graph annotations from each application. However, graph tasks with node level, edge level, and graph level are far diversified, making the pre-training pretext often incompatible with these multiple tasks. This gap may even cause a "negative transfer" to the specific application, leading to poor results. Inspired by the prompt learning in natural language processing (NLP), which has presented significant effectiveness in leveraging prior knowledge for various NLP tasks, we study the prompting topic for graphs with the motivation of filling the gap between pre-trained models and various graph tasks. In this paper, we propose a novel multi-task prompting method for graph models. Specifically, we first unify the format of graph prompts and language prompts with the prompt token, token structure, and inserting pattern. In this way, the prompting idea from NLP can be seamlessly introduced to the graph area. Then, to further narrow the gap between various graph tasks and state-of-the-art pre-training strategies, we further study the task space of various graph applications and reformulate downstream problems to the graph-level task. Afterward, we introduce meta-learning to efficiently learn a better initialization for the multi-task prompt of graphs so that our prompting framework can be more reliable and general for different tasks. We conduct extensive experiments, results from which demonstrate the superiority of our method. Copyright © 2023, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

SmartBlock: An Approach to Standardizing In Situ Workflow Components

SmartBlock: An Approach to Standardizing In Situ Workflow Co...

引用

IEEE International Symposium on Parallel and Distributed Processing Workshops and Phd Forum (IPDPSW)

作者： Alexis Champsaur Jay Lofstead Jai Dayal Matthew Wolf Greg Eisenhauer Patrick Widener Ada Gavrilovska School of Computer Science Atlanta GA USA Scalable System Software Group Sandia National Laboratories Albuquerque NM USA Scientific Data Group Oak Ridge National Lab Oak Ridge TN USA

Multi-step scientific workflows have become prominent and powerful tools of data-driven scientific discovery. Run-time analytic techniques are now commonly used to mitigate the performance effects of using parallel file systems as staging areas during workflow execution. However, workflow construction and deployment for extreme-scale computing is still largely an ad hoc process with uneven support from existing tools. In this paper, we present SMARTBLOCK, an approach to designing generic, reusable components for end-to-end construction of workflows. Specifically, we demonstrate that a small set of SMARTBLOCK generic components can be reused to build a diverse set of workflows, using examples based on actual analytic processes with three well-known scientific codes. Our evaluation shows promising scaling properties as well as negligible overheads for using a modular approach over a custom, "all-in-one" solution. As extreme-scale systems incorporate data analytics on simulation data as it is generated at rates that far outstrip available I/O bandwidth, tools such as SMARTBLOCK will become increasingly valuable for defining and deploying flexible, efficient workflows.

关键词： Tools data models Engines Analytical models data analysis Complexity theory Electronic mail

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：