检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Momeni, Ali Rahmani, Babak Scellier, Benjamin Wright, Logan G. McMahon, Peter L. Wanjura, Clara C. Li, Yuhang Skalli, Anas Berloff, Natalia G. Onodera, Tatsuhiro Oguz, Ilker Morichetti, Francesco del Hougne, Philipp Le Gallo, Manuel Sebastian, Abu Mirhoseini, Azalia Zhang, Cheng Marković, Danijela Brunner, Daniel Moser, Christophe Gigan, Sylvain Marquardt, Florian Ozcan, Aydogan Grollier, Julie Liu, Andrea J. Psaltis, Demetri Alù, Andrea Fleury, Romain Lausanne Switzerland Microsoft Research 198 Cambridge Science Park CambridgeCB4 0AB United Kingdom Rain AI San Francisco United States Department of Applied Physics Yale University CT United States School of Applied and Engineering Physics Cornell University IthacaNY14853 United States Max Planck Institute for the Science of Light Staudtstraße 2 Erlangen91058 Germany Department of Electrical and Computer Engineering University of California Los AngelesCA90095 United States FEMTO-ST Institute Optics Department CNRS University Bourgogne Franche-Comté Besançon25030 Cedex France Department of Applied Mathematics and Theoretical Physics University of Cambridge Cambridge United Kingdom NTT Physics and Informatics Laboratories NTT Research Inc. Sunnyvale United States Lausanne Switzerland Dipartimento di Elettronica Informazione e Bioingegneria Politecnico di Milano Milan Italy Univ Rennes CNRS IETR UMR 6164 RennesF-35000 France IBM Research Europe– Zurich Rüschlikon8803 Switzerland Department of Computer Science Stanford University United States Google DeepMind 1600 Amphitheatre Parkway Mountain ViewCA94043 United States Unité Mixte de Physique CNRS/Thales CNRS Thales Université Paris-Saclay Palaiseau France Laboratoire Kastler Brossel Sorbonne Université École Normale Supérieure Collège de France CNRS UMR 8552 Paris France Laboratoire Albert Fert CNRS Thales UniversitéParis-Saclay Palaiseau91767 France Department of Physics and Astronomy University of Pennsylvania PhiladelphiaPA19104 United States Lausanne Switzerland Photonics Initiative Advanced Science Research Center City University of New York New YorkNY10031 United States Physics Program Graduate Center City University of New York New YorkNY10016 United States

Physical neural networks (PNNs) are a class of neural-like networks that leverage the properties of physical systems to perform computation. While PNNs are so far a niche research area with small-scale laboratory demonstrations, they are arguably one of the most underappreciated important opportunities in modern artificial intelligence (ai). Could we train ai models 1000x larger than current ones? Could we do this and also have them perform inference locally and privately on edge devices, such as smartphones or sensors? Research over the past few years has shown that the answer to all these questions is likely "textityes, with enough research": PNNs could one day radically change what is possible and practical for ai systems. To do this will however require rethinking both how ai models work, and how they are trained – primarily by considering the problems through the constraints of the underlying hardware physics. To train PNNs at large scale, many methods including backpropagation-based and backpropagation-free approaches are now being explored. These methods have various trade-offs, and so far no method has been shown to scale to the same scale and performance as the backpropagation algorithm widely used in deep learning today. However, this is rapidly changing, and a diverse ecosystem of training techniques provides clues for how PNNs may one day be utilized to create both more efficient realizations of current-scale ai models, and to enable unprecedented-scale models. Copyright © 2024, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Limits of Private Learning with Access to Public Data

arXiv

引用

arXiv 2019年

作者： Alon, Noga Bassily, Raef Moran, Shay Department of Mathematics Princeton University Department of Computer Science & Engineering Ohio State University Google AI Princeton

We consider learning problems where the training set consists of two types of examples: private and public. The goal is to design a learning algorithm that satisfies differential privacy only with respect to the private examples. This setting interpolates between private learning (where all examples are private) and classical learning (where all examples are public). We study the limits of learning in this setting in terms of private and public sample complexities. We show that any hypothesis class of VC-dimension d can be agnostically learned up to an excess error of α using only (roughly) d/α public examples and d/α2 private labeled examples. This result holds even when the public examples are unlabeled. This gives a quadratic improvement over the standard d/α2 upper bound on the public sample complexity (where private examples can be ignored altogether if the public examples are labeled). Furthermore, we give a nearly matching lower bound, which we prove via a generic reduction from this setting to the one of private learning without public data. Copyright © 2019, The Authors. All rights reserved.

关键词： Learning algorithms

来源：评论

学校读者我要写书评

暂无评论

Coordinating complementary waveforms for suppressing range sidelobes in a Doppler band

arXiv

引用

arXiv 2020年

作者： Dang, Wenbing Pezeshki, Ali Howard, Stephen D. Moran, William Calderbank, Robert Department of Electrical and Computer Engineering Colorado State University Fort CollinsCO80523-1373 United States Argo AI Mountain ViewCA94041 United States Department of Electrical and Computer Engineering Department of Mathematics Colorado State University Fort CollinsCO80523-1373 United States Defence Science and Technology Group P.O. Box 1500 EdinburghSA5111 Australia Department of Electrical and Electronic Engineering University of Melbourne MelbourneVIC3010 Australia Department of Electrical Engineering Department of Computer Science Department of Mathematics at Duke University DurhamNC27708 United States

We present a general method for constructing radar transmit pulse trains and receive filters for which the radar point-spread function in delay and Doppler (radar cross-ambiguity function) is essentially free of range sidelobes inside a Doppler interval around the zero-Doppler axis. The transmit and receive pulse trains are constructed by coordinating the transmission of a pair of Golay complementary waveforms across time according to zeros and ones in a binary sequence P. In the receive pulse train filter, each waveform is weighted according to an element from another sequence Q. We show that the spectrum of essentially the product of P and Q sequences controls the size of the range sidelobes of the cross-ambiguity function. We annihilate the range sidelobes at low Doppler by designing the (P, Q) pairs such that their products have high-order spectral nulls around zero Doppler. We specify the subspace, along with a basis, for such sequences, thereby providing a general way of constructing (P, Q) pairs. At the same time, the signal-to-noise ratio (SNR) at the receiver output, for a single point target in white noise, depends only on the choice of Q. By jointly designing the transmit-receive sequences (P, Q), we can maximize the output SNR subject to achieving a given order of the spectral null. The proposed (P, Q) constructions can also be extended to sequences consisting of more than two complementary waveforms;this is done explicitly for a library of Golay complementary quads. Finally, we extend the construction of (P, Q) pairs to multiple-input-multiple-output (MIMO) radar, by designing transmit-receive pairs of paraunitary waveform matrices whose matrix-valued cross-ambiguity function is essentially free of range sidelobes inside a Doppler interval around the zero-Doppler axis. Copyright © 2020, The Authors. All rights reserved.

关键词： MIMO systems

来源：评论

学校读者我要写书评

暂无评论

A Robust Attentional Framework for License Plate Recognition in the Wild

arXiv

引用

arXiv 2020年

作者： Zhang, Linjiang Wang, Peng Li, Hui Li, Zhen Shen, Chunhua Zhang, Yanning School of Computer Science Northwestern Polytechnical University Xi’an China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology China School of Computer Science University of Adelaide SA5005 Australia big data and AI technology department Minsheng Fintech Corp. LTD.

Recognizing car license plates in natural scene images is an important yet still challenging task in realistic applications. Many existing approaches perform well for license plates collected under constrained conditions, e.g., shooting in frontal and horizontal view-angles and under good lighting conditions. However, their performance drops significantly in an unconstrained environment that features rotation, distortion, occlusion, blurring, shading or extreme dark or bright conditions. In this work, we propose a robust framework for license plate recognition in the wild. It is composed of a tailored CycleGAN model for license plate image generation and an elaborate designed image-to-sequence network for plate recognition. On one hand, the CycleGAN based plate generation engine alleviates the exhausting human annotation work. Massive amount of training data can be obtained with a more balanced character distribution and various shooting conditions, which helps to boost the recognition accuracy to a large extent. On the other hand, the 2D attentional based license plate recognizer with an Xception-based CNN encoder is capable of recognizing license plates with different patterns under various scenarios accurately and robustly. Without using any heuristics rule or post-processing, our method achieves the state-of-the-art performance on four public datasets, which demonstrates the generality and robustness of our framework. Moreover, we released a new license plate dataset, named "CLPD", with 1200 images from all 31 provinces in mainland China. The dataset can be available from: https://***/wangpengnorman/CLPD_dataset. Copyright © 2020, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

The INTERSPEECH 2020 far-field speaker verification challenge

arXiv

引用

arXiv 2020年

作者： Qin, Xiaoyi Li, Ming Bu, Hui Rao, Wei Das, Rohan Kumar Narayanan, Shrikanth Li, Haizhou Data Science Research Center Duke Kunshan University Kunshan China Department of Electrical & Computer Engineering National University of Singapore Singapore Signal Analysis and Interpretation Lab University of Southern California Los Angeles United States AI Shell Foundation Beijing China School of Computer Science Wuhan University Wuhan China

The INTERSPEECH 2020 Far-Field Speaker Verification Challenge (FFSVC 2020) addresses three different research problems under well-defined conditions: far-field text-dependent speaker verification from single microphone array, far-field text-independent speaker verification from single microphone array, and far-field text-dependent speaker verification from distributed microphone arrays. All three tasks pose a cross-channel challenge to the participants. To simulate the real-life scenario, the enrollment utterances are recorded from close-talk cellphone, while the test utterances are recorded from the far-field microphone arrays. In this paper, we describe the database, the challenge, and the baseline system, which is based on a ResNet-based deep speaker network with cosine similarity scoring. For a given utterance, the speaker embeddings of different channels are equally averaged as the final embedding. The baseline system achieves minDCFs of 0.62, 0.66, and 0.64 and EERs of 6.27%, 6.55%, and 7.18% for task 1, task 2, and task 3, respectively. Copyright © 2020, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Correction: VER-Net: a hybrid transfer learning model for lung cancer detection using CT scan images

引用

BMC medical imaging 2024年第1期24卷 128页

作者： Anindita Saha Shahid Mohammad Ganie Pijush Kanti Dutta Pramanik Rakesh Kumar Yadav Saurav Mallik Zhongming Zhao Department of Computing Science and Engineering IFTM University Moradabad Uttar Pradesh India. AI Research Centre Department of Analytics School of Business Woxsen University Hyderabad Telangana 502345 India. School of Computer Applications and Technology Galgotias University Greater Noida Uttar Pradesh 203201 India. pijushjld@yahoo.co.in. Department of Computer Science & Engineering MSOET Maharishi University of Information Technology Lucknow Uttar Pradesh India. Department of Environmental Health Harvard T. H. Chan School of Public Health Boston MA USA. Center for Precision Health McWilliams School of Biomedical Informatics The University of Texas Health Science Center at Houston Houston TX 77030 USA. zhongming.zhao@uth.tmc.edu.

来源：评论

学校读者我要写书评

暂无评论

CN-Celeb: Multi-genre speaker recognition

arXiv

引用

arXiv 2020年

作者： Li, Lantian Liu, Ruiqi Kang, Jiawen Fan, Yue Cui, Hao Cai, Yunqi Vipperla, Ravichander Zheng, Thomas Fang Wang, Dong BNRist at Tsinghua University Beijing China China University of Mining and Technology Beijing China Department of Systems Engineering and Engineering Management Chinese University of Hong Kong China Department of Computer Science and Technology Tsinghua University China Samsung AI Center Cambridge United Kingdom Key Laboratory of Transient Physics Nanjing University of Science and Technology China

Research on speaker recognition is extending to address the vulnerability in the wild conditions, among which genre mismatch is perhaps the most challenging, for instance, enrollment with reading speech while testing with conversational or singing audio. This mismatch leads to complex and composite inter-session variations, both intrinsic (i.e., speaking style, physiological status) and extrinsic (i.e., recording device, background noise). Unfortunately, the few existing multi-genre corpora are not only limited in size but are also recorded under controlled conditions, which cannot support conclusive research on the multi-genre problem. In this work, we firstly publish CN-Celeb, a large-scale multi-genre corpus that includes in-the-wild speech utterances of 3,000 speakers in 11 different genres. Secondly, using this dataset, we conduct a comprehensive study on the multi-genre phenomenon, in particular the impact of the multi-genre challenge on speaker recognition and the performance gain when the new dataset is used to conduct multi-genre training. Copyright © 2020, The Authors. All rights reserved.

关键词： Music

来源：评论

学校读者我要写书评

暂无评论

AutoGAN: Neural architecture search for generative adversarial networks

arXiv

引用

arXiv 2019年

作者： Gong, Xinyu Chang, Shiyu Jiang, Yifan Wang, Zhangyang Department of Computer Science & Engineering Texas A&M University MIT-IBM Watson AI Lab

Neural architecture search (NAS) has witnessed prevailing success in image classification and (very recently) segmentation tasks. In this paper, we present the first preliminary study on introducing the NAS algorithm to generative adversarial networks (GANs), dubbed AutoGAN. The marriage of NAS and GANs faces its unique challenges. We define the search space for the generator architectural variations and use an RNN controller to guide the search, with parameter sharing and dynamic-resetting to accelerate the process. Inception score is adopted as the reward, and a multi-level search strategy is introduced to perform NAS in a progressive way. Experiments validate the effectiveness of AutoGAN on the task of unconditional image generation. Specifically, our discovered architectures achieve highly competitive performance compared to current state-of-the-art hand-crafted GANs, e.g., setting new state-of-the-art FID scores of 12.42 on CIFAR-10, and 31.01 on STL-10, respectively. We also conclude with a discussion of the current limitations and future potential of AutoGAN. The code is avaliable at https://***/TAMU-VITA/ AutoGAN. Copyright © 2019, The Authors. All rights reserved.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Calibrated domain-invariant learning for highly generalizable large scale re-identification

arXiv

引用

arXiv 2019年

作者： Yuan, Ye Chen, Wuyang Chen, Tianlong Yang, Yang Ren, Zhou Wang, Zhangyang Hua, Gang Department of Computer Science and Engineering Texas A&M University Walmart Technology Wormpex AI Research

Many real-world applications, such as city scale traffic monitoring and control, requires large scale re-identification. However, previous ReID methods often failed to address two limitations in existing ReID benchmarks, i.e., low spatiotemporal coverage and sample imbalance. Notwithstanding their demonstrated success in every single benchmark, they have difficulties in generalizing to unseen environments. As a result, these methods are less applicable in a large scale setting due to poor generalization. In seek for a highly generalizable large-scale ReID method, we present an adversarial domain-invariant feature learning framework (ADIN) that explicitly learns to separate identity-related features from challenging variations, where for the first time "free" annotations in ReID data such as video timestamp and camera index are utilized. Furthermore, we find that the imbalance of nuisance classes jeopardizes the adversarial training, and for mitigation we propose a calibrated adversarial loss that is attentive to nuisance distribution. Experiments on existing large-scale person/vehicle ReID datasets demonstrate that ADIN learns more robust and generalizable representations, as evidenced by its outstanding direct transfer performance across datasets, which is a criterion that can better measure the generalizability of large scale Re-ID methods. Copyright © 2019, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

A multi-objective deep reinforcement learning algorithm for spatio-temporal latency optimization in mobile IoT-enabled edge computing networks

引用

Simulation Modelling Practice and Theory 2025年 143卷

作者： Khoshvaght, Parisa Haider, Amir Rahmani, Amir Masoud Gharehchopogh, Farhad Soleimanian Anka, Ferzat Lansky, Jan Hosseinzadeh, Mehdi Institute of Research and Development Duy Tan University Da Nang Viet Nam School of Engineering & Technology Duy Tan University Da Nang Viet Nam Centre for Research Impact & Outcome Chitkara University Institute of Engineering and Technology Chitkara University Punjab Rajpura140401 India Department of AI and Robotics Sejong University Seoul05006 Korea Republic of Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Engineering Ur. C. Islamic Azad University Urmia Iran Fatih Sultan Mehmet Vakif University Istanbul Turkey Department of Computer Science and Mathematics Faculty of Economic Studies University of Finance and Administration Prague Czech Republic Pattern Recognition and Machine Learning Laboratory School of Computing Gachon University Seongnam Korea Republic of

The rapid increase in Mobile Internet of Things (IoT) devices requires novel computational frameworks. These frameworks must meet strict latency and energy efficiency requirements in Edge and Mobile Edge Computing (MEC) systems. Spatio-temporal dynamics, which include the position of edge servers and the timing of task schedules, pose a complex optimization problem. These challenges are further exacerbated by the heterogeneity of IoT workloads and the constraints imposed by device mobility. The balance between computational overhead and communication challenges is also a problem. To solve these issues, advanced methods are needed for resource management and dynamic task scheduling in mobile IoT and edge computing environments. In this paper, we propose a Deep Reinforcement Learning (DRL) multi-objective algorithm, called a Double Deep Q-Learning (DDQN) framework enhanced with Spatio-temporal mobility prediction, latency-aware task offloading, and energy-constrained IoT device trajectory optimization for federated edge computing networks. DDQN was chosen for its optimize stability and reduced overestimation in Q-values. The framework employs a reward-driven optimization model that dynamically prioritizes latency-sensitive tasks, minimizes task migration overhead, and balances energy efficiency across devices and edge servers. It integrates dynamic resource allocation algorithms to address random task arrival patterns and real-time computational demands. Simulations demonstrate up to a 35 % reduction in end-to-end latency, a 28 % improvement in energy efficiency, and a 20 % decrease in the deadline-miss ratio compared to benchmark algorithms. © 2025 Elsevier B.V.

关键词： Resource allocation

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：