检索结果-内蒙古大学图书馆

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Zhaokun Zhou Yijie Lu Yanhao Jia Kaiwei Che Jun Niu Liwei Huang Xinyu Shi Yuesheng Zhu Guoqi Li Zhaofei Yu Li Yuan School of Electronic and Computer Engineering Shenzhen Graduate School Peking University and Peng Cheng Laboratory School of Electronic and Computer Engineering Shenzhen Graduate School Peking University College of Computing and Data Science Nanyang Technological University and Deep NeuroCognition Lab I2R and CFAR Agency for Science Technology and Research School of Computer Science Peking University and Peng Cheng Laboratory Institute for Artificial Intelligence Peking University and School of Computer Science Peking University Institute of Automation Chinese Academy of Sciences and Peng Cheng Laboratory

ISBN: (纸本)9798331314385

Spiking Neural Networks (SNNs) provide a sparse spike-driven mechanism which is believed to be critical for energy-efficient deep learning. Mixture-of-Experts (MoE), on the other side, aligns with the brain mechanism of distributed and sparse processing, resulting in an efficient way of enhancing model capacity and conditional computation. In this work, we consider how to incorporate SNNs' spike-driven and MoE's conditional computation into a unified framework. However, MoE uses softmax to get the dense conditional weights for each expert and TopK to hard-sparsify the network, which does not fit the properties of SNNs. To address this issue, we reformulate MoE in SNNs and introduce the Spiking Experts Mixture Mechanism (SEMM) from the perspective of sparse spiking activation. Both the experts and the router output spiking sequences, and their element-wise operation makes SEMM computation spike-driven and dynamic sparse-conditional. By developing SEMM into Spiking Transformer, the Experts Mixture Spiking Attention (EMSA) and the Experts Mixture Spiking Perceptron (EMSP) are proposed, which performs routing allocation for head-wise and channel-wise spiking experts, respectively. Experiments show that SEMM realizes sparse conditional computation and obtains a stable improvement on neuromorphic and static datasets with approximate computational overhead based on the Spiking Transformer baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Evaluation of the Neural-network-based Method to Discover Sets and Representatives of Nonlinearly Dependent Variables 5

Evaluation of the Neural-network-based Method to Discover Se...

引用

5th IEEE International Conference on Cybernetics, CYBCONF 2021

作者： Ohsaki, Miho Sasaki, Hayato Kishimoto, Naoya Katagiri, Shigeru Ohnishi, Kei Sebastian, Yakub Then, Patrick Doshisha University Graduate School of Science and Engineering Kyotanabe Japan Doshisha University Department of Information Systems Design Kyotanabe Japan Charles Darwin University College of Engineering Information Technology and Environment Casuarina Australia Swinburne University of Technology Faculty of Engineering Computing and Science Sarawak Malaysia

ISBN: (纸本)9781665403207

It is desired in a variety of fields to identify which variables are dependent, and variable dependence measures have been studied. The majority of such measures detect a linear or a certain range of nonlinear dependence between paired variables. To go beyond them, a method based on Neural Network Regression, Group Lasso, and Information Aggregation has been proposed in our past study. It can detect a wide range of nonlinear dependences among multi variables and discover the sets and representatives of the detected dependences. Its fundamental effectiveness has already been examined using synthesized artificial datasets containing a single dependence. For further evaluation in the present study, we conducted an experiment using those containing multi dependences. The proposed method succeeded in discovering the sets and representatives, and its performance was robust to data size and noise rate. The experimental results suggested that the proposed method works well for difficult tasks to handle multi dependences. © 2021 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Automatic Epidermis Segmentation in Fluorescence Images Based on a U-Shaped Network Model

Automatic Epidermis Segmentation in Fluorescence Images Base...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Herng-Hua Chang Yu-Xuan Chou Chi-Chao Chao Sung-Tsang Hsieh Department of Engineering Science and Ocean Engineering Scientific Computing and Intelligent Learning Laboratory National Taiwan University Taipei Taiwan Department of Neurology and Stroke Center National Taiwan University Hospital Taipei Taiwan Graduate Institute of Anatomy and Cell Biology National Taiwan University Taipei Taiwan

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Small fiber neuropathy analysis in the epidermis of the skin is critical to the diagnosis of various diseases such as diabetes mellitus and familial amyloid polyneuropathy. Intraepidermal nerve fiber examination plays an important role to serve as a highly sensitive indicator of sensory nerve fiber damage. Segmentation of the epidermis region is a prior image processing task for subsequent image analysis. Due to the lack of suitable and available tools for this specific task, this paper investigates an automatic epidermis segmentation framework in skin fluorescence images. To maintain the high resolution and increase the image amount, the original image is decomposed into a series of sub-images for model input. A U-shaped network structure consisting of five block layers with different depths is proposed for epidermis segmentation. Each model block is designed in a multi-scale manner, which is composed of two different convolution kernel pipelines. By combining and sharing the information from these model blocks with skip connections between them, we can effectively increase the diversity of the feature maps for more accurate segmentation. Experiments on in-house epidermis images demonstrated the advantages of the proposed epidermis segmentation network, which outperformed many state-of-the-art deep learning-based segmentation models. The proposed network architecture is potential in facilitating the epidermis segmentation task for further small fiber neuropathy research.

关键词： Image segmentation Optical fiber sensors Nerve fibers Accuracy Image resolution Pipelines Diversity reception

来源：评论

学校读者我要写书评

暂无评论

Releasing ARP data with differential privacy guarantees for LAN anomaly detection 18

Releasing ARP data with differential privacy guarantees for ...

引用

18th International Conference on Electrical engineering/Electronics, Computer, Telecommunications and Information Technology, ECTI-CON 2021

作者： Rattanavipanon, Norrathep Ponnoprat, Donlapark Ochiai, Hideya Tantayakul, Kuljaree Angchuan, Touchai Kamolphiwong, Sinchai Prince of Songkla University College of Computing Chiang Mai University Department of Statistics The University of Tokyo Graduate School of Information Science and Technology Japan Prince of Songkla University Faculty of Engineering

ISBN: (纸本)9780738111278

Anomaly detection has emerged as a popular technique for detecting malicious behaviors in local area networks (LANs). Various aspects of LAN anomaly detection have been widely studied. Nonetheless, the privacy concern about individual users or their relationship in LAN has not been thoroughly explored in the prior work. In some realistic cases, the anomaly detection analysis needs to be carried out by an external party, located outside the LAN. Thus, it is important for the LAN admin to release LAN data to this party in a private way in order to reveal no information about LAN users;at the same time, the released data must also preserve the utility of being able to detect anomalies. This paper investigates the possibility of privately releasing ARP data that can later be used to identify anomalies in LAN. We present two approaches and show that they satisfy different levels of differential privacy - a rigorous and provable notion for quantifying privacy loss in a system. Our real-world experimental results confirm practical feasibility of our approaches. With a proper privacy budget, both of our approaches preserve more than 90% utility of the released data. © 2021 IEEE.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

External quantum fluctuations select measurement contexts

arXiv

引用

arXiv 2025年

作者： Hance, Jonte R. Ji, Ming Matsushita, Tomonori Hofmann, Holger F. School of Computing Newcastle University 1 Science Square Newcastle upon TyneNE4 5TG United Kingdom Quantum Engineering Technology Laboratories Department of Electrical and Electronic Engineering University of Bristol Woodland Road BristolBS8 1US United Kingdom QICI Quantum Information and Computation Initiative School of Computing and Data Science The University of Hong Kong Pokfulam Road Hong Kong Graduate School of Advanced Science and Engineering Hiroshima University Kagamiyama 1-3-1 Higashi Hiroshima739-8530 Japan

Quantum paradoxes show that the outcomes of different quantum measurements cannot be described by a single measurement-independent reality. Any theoretical description of a quantum measurement implies the selection of a specific measurement context. Here, we investigate generalised quantum measurements, in order to identify the mechanism by which this specific context is selected. We show that external quantum fluctuations, represented by the initial state of the measurement apparatus, play an essential role in the selection of the context. This has the nontrivial consequence that, when considering measurements other than just idealised projection-valued measures, different outcomes of a single measurement setup can represent different measurement contexts. We further show this result underpins recent claims that contextuality can occur in scenarios without measurement incompatibility. Copyright © 2025, The Authors. All rights reserved.

关键词： Velocity measurement

来源：评论

学校读者我要写书评

暂无评论

General-Purpose Quantum Circuit Generator for Partially Fault-Tolerant Quantum computing Architecture

General-Purpose Quantum Circuit Generator for Partially Faul...

引用

Quantum computing and engineering (QCE), IEEE International Conference on

作者： Yutaro Akahoshi Jun Fujisaki Hirotaka Oshima Shintaro Sato Keisuke Fujii Quantum Laboratory Fujitsu Research Fujitsu Limited Kanagawa Japan Fujitsu Quantum Computing Joint Research Division Center for Quantum Information and Quantum Biology Osaka University Toyonaka Osaka Japan Graduate School of Engineering Science Osaka University Toyonaka Osaka Japan RIKEN Center for Quantum Computing (RQC) Wako Saitama Japan

ISBN: (数字)9798331541378

ISBN: (纸本)9798331541385

Quantum computers hold the promise of revolutionizing several computational tasks by significantly enhancing their calculation speed compared to classical computers. However, there is still a large gap towards fault-tolerant quantum computing (FTQC) due to the large requirement of physical qubits. Under these circumstances, authors proposed a partially fault-tolerant quantum computing architecture that consists of the fault-tolerant Clifford gates and the sufficiently clean analog rotation gate, named “Space-Time efficient Analog Rotation gate quantum computing architecture (STAR architecture).” Although its theoretical foundation is given, we need to develop an efficient software implementation tailored for STAR architecture due to its unique choice of the fundamental gate set. In this study, we construct an integrated software system of STAR-architecture-based quantum computation, which generates physical instructions executable on quantum devices from input logical quantum circuits. The system mainly consists of two parts, a circuit converter and an operation controller. The circuit converter comprises a set of conversion subroutines, which bridge several instruction layers: logical circuit layer, lattice surgery layer, and physical circuit layer. The operation controller efficiently executes the generated instructions. Especially, it enables efficient treatment of the analog rotation gate, which needs real-time scheduling of running instructions due to its probabilistic nature.

关键词： Computers Fault tolerance Quantum computing Fault tolerant systems Stars Quantum mechanics Surgery Computer architecture Logic gates Quantum circuit

来源：评论

学校读者我要写书评

暂无评论

Provably secure fog-based authentication protocol for VANETs

引用

Computer Networks 2024年 246卷

作者： Awais, Syed Muhammad Yucheng, Wu Mahmood, Khalid Badar, Hafiz Muhammad Sanaullah Kharel, Rupak Das, Ashok Kumar School of Microelectronics and Communication Engineering Chongqing University Chongqing China Graduate School of Intelligent Data Science National Yunlin University of Science and Technology Yunlin Douliu64002 Taiwan Department of Emerging Computing Technologies Emerson University Multan Pakistan School of Computing and Engineering University of Huddersfield HuddersfieldHD1 3DH United Kingdom The Faculty of Electrical and Electronics Engineering Ton Duc Thang University Ho Chi Minh City Viet Nam Center for Security Theory and Algorithmic Research International Institute of Information Technology Hyderabad500 032 India

The integration of fog computing and vehicular ad-hoc networks (VANETs) has become increasingly important due to advancements in cloud computing, Internet of Things (IoT) technologies, and intelligent transportation systems. However, ensuring secure communication in fog-based VANETs poses a significant challenge. To address this challenge, we propose a novel authenticated key agreement protocol that achieves mutual authentication, generates a secure session key for confidential communication, and ensures privacy protection without relying on bilinear pairing. We provide rigorous security proofs for our protocol, specifically tailored for fog-based VANETs, demonstrating its ability to meet their stringent security requirements. Simulations using NS3 allow for a comprehensive performance evaluation, providing insights into the protocol's efficiency and scalability. Additionally, our protocol is highly efficient, featuring low computation and communication costs, thereby offering a practical and scalable solution for secure communication in fog-based VANETs. © 2024

关键词： Fog

来源：评论

学校读者我要写书评

暂无评论

Dense Coding with Locality Restriction on Decoders: Quantum Encoders versus Superquantum Encoders

引用

PRX Quantum 2022年第3期3卷 030346-030346页

作者： Masahito Hayashi Kun Wang Shenzhen Institute for Quantum Science and Engineering Southern University of Science and Technology Shenzhen 518055 China Guangdong Provincial Key Laboratory of Quantum Science and Engineering Southern University of Science and Technology Shenzhen 518055 China Graduate School of Mathematics Nagoya University Nagoya 464-8602 Japan Institute for Quantum Computing Baidu Research Beijing 100193 China

We investigate practical dense coding by imposing locality restrictions on decoders and symmetry restrictions on encoders within the resource theory of asymmetry framework. In this task, the sender Alice and the helper Fred preshare an entangled state. Alice encodes a classical message into the quantum state using a symmetric preserving encoder and sends the encoded state to Bob through a noiseless quantum channel. The receiver Bob and helper Fred are limited to performing quantum measurements satisfying certain locality restrictions to decode the classical message. We are interested in the ultimate dense coding capacity under these constraints. Our contributions are summarized as follows. First, we derive both one-shot and asymptotic optimal achievable transmission rates of the dense coding task under different encoder and decoder combinations. Surprisingly, our results reveal that the transmission rate cannot be improved even when the decoder is relaxed from one-way local operations and classical communication (LOCC) to two-way LOCC, separable measurements, and partial transpose positive measurements of the bipartite system. Second, depending on the class of allowed decoders with certain locality restrictions, we relax the class of encoding operations to superquantum encoders in the general probability theory framework and derive dense coding transmission rates under this setting. For example, when the decoder is fixed to a separable measurement, theoretically, a positive operation is allowed as an encoding operation. Remarkably, even under this superquantum relaxation, the transmission rate still cannot be lifted. This fact highlights the universal validity of our analysis on practical dense coding beyond quantum theory.

关键词： Quantum channels Quantum communication Quantum entanglement Resource theories

来源：评论

学校读者我要写书评

暂无评论

Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling

arXiv

引用

arXiv 2023年

作者： Zhao, Jingwei Xia, Gus Wang, Ziyu Wang, Ye Institute of Data Science NUS Singapore School of Computing NUS Singapore Integrative Sciences and Engineering Programme NUS Graduate School Singapore Machine Learning Department MBZUAI United Arab Emirates Computer Science Department NYU Shanghai China

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing computational efficiency. In this paper, we introduce a novel system that leverages prior modelling over disentangled style factors to address these challenges. Our method presents a two-stage process: initially, a piano arrangement is derived from the lead sheet by retrieving piano texture styles;subsequently, a multi-track orchestration is generated by infusing orchestral function styles into the piano arrangement. Our key design is the use of vector quantization and a unique multi-stream Transformer to model the long-term flow of the orchestration style, which enables flexible, controllable, and structured music generation. Experiments show that by factorizing the arrangement task into interpretable sub-stages, our approach enhances generative capacity while improving efficiency. Additionally, our system supports a variety of music genres and provides style control at different composition hierarchies. We further show that our system achieves superior coherence, structure, and overall arrangement quality compared to existing baselines. © 2023, CC BY.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Cyberoception: Finding A Painlessly-Measurable New Sense In The Cyberworld Towards Emotion-awareness In computing 25

Cyberoception: Finding A Painlessly-Measurable New Sense In ...

引用

2025 CHI Conference on Human Factors in computing Systems, CHI 2025

作者： Okoshi, Tadashi Gao, Zexiong Tan, Yi Zhen Karasawa, Takumi Miki, Takeshi Sasaki, Wataru Balan, Rajesh Krishna Faculty of Environment and Information Studies Keio University Kanagawa Fujisawa Japan Graduate School of Interdisciplinary Information Studies The University of Tokyo Tokyo Tokyo Japan School of Computing and Information Systems Singapore Management University Singapore Singapore Singapore Graduate School of Media and Governance Keio University Kanagawa Pref Fujisawa city Japan Department of Engineering University of Cambridge Cambridge Cambridge United Kingdom Graduate School of Science and Technology Nara Institute of Science and Technology Nara Ikoma Japan

ISBN: (纸本)9798400713941

In Affective computing, recognizing users' emotions accurately is the basis of affective human-computer interaction. Understanding users' interoception contributes to a better understanding of individually different emotional abilities, which is essential for achieving inter-individually accurate emotion estimation. However, existing interoception measurement methods, such as the heart rate discrimination task, have several limitations, including their dependence on a well-controlled laboratory environment and precision apparatus, making monitoring users' interoception challenging. This study aims to determine other forms of data that can explain users' interoceptive or similar states in their real-world lives and propose a novel hypothetical concept "cyberoception,"a new sense (1) which has properties similar to interoception in terms of the correlation with other emotion-related abilities, and (2) which can be measured only by the sensors embedded inside commodity smartphone devices in users' daily lives. Results from a 10-day-long in-lab/in-the-wild hybrid experiment reveal a specific cyberoception type "Turn On"(users' subjective sensory perception about the frequency of turning-on behavior on their smartphones) significantly related to participants' emotional valence. We anticipate that cyberoception to serve as a fundamental building block for developing more "emotion-aware", user-friendly applications and services. © 2025 Copyright held by the owner/author(s).

关键词： Cyberoception Emotion / Affective computing Interoception Mobile Devices Personalization Sensing Wearable Devices

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：