检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Shaokang Wang Guoqing Xiang Jinchang Xu Shanghang Zhang Xiaodong Xie School of Computer Science Peking University Beijing China Alibaba Cloud Computing Beijing China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Neural image compression has achieved significant advancements, consistently outperforming traditional codecs in terms of performance. However, research on quality control algorithms for neural image compression is still lacking. In this paper, we propose a framework designed to control the quality of compressed images through a one-pass pre-analysis. First, we construct a foundational relationship between the quantization factor and compression distortion, utilizing variable rate neural image compression as the basis for quality control. Second, we introduce the image Content-Compression features-based Distortion Estimation Network (C 2 DEN) to efficiently fit the sample-adaptive Quantization-Distortion (QD) model. Leveraging the QD model, we convert the target quality into a quantization factor to control the compression model, enabling quality-controllable compression of samples. Experimental results show that the average quality errors on four different datasets are only 0.89%, 1.79%, 1.73%, and 1.61%. Compared with existing control methods, our method reduces the algorithm time complexity by 98.58%, 98.52%, 98.85%, and 98.50% while ensuring accuracy, which further demonstrates the superiority of our method.

关键词： Image coding Quantization (signal) Acoustic distortion Signal processing algorithms Rate-distortion Estimation Quality control Rate distortion theory Time complexity Speech processing

来源：评论

学校读者我要写书评

暂无评论

Research progress of quantum artificial intelligence in smart city

引用

Intelligent and Converged Networks 2024年第2期5卷 116-133页

作者： Sumin Wang Ning Wang Tongyu Ji Yiyun Shi Chao Wang the Joint International Research Laboratory of Specialty Fiber Optics and Advanced Communication Shanghai UniversityShanghai 200444China School of Information Engineering Ganzhou Key Laboratory of Cloud Computing and Big Data ResearchGannan University of Science and TechnologyGanzhou 341000China

The rapid accumulation of big data in the Internet era has gradually decelerated the progress of Artificial Intelligence(AI).As Moore’s Law approaches its limit,it is imperative to break the constraints that are holding back artificial *** computing and artificial intelligence have been advancing along the highway of human civilization for many years,emerging as new engines driving economic and social *** article delves into the integration of quantum computing and artificial intelligence in both research and *** introduces the capabilities of both universal quantum computers and special-purpose quantum computers that leverage quantum *** discussion further explores how quantum computing enhances classical artificial intelligence from four perspectives:quantum supervised learning,quantum unsupervised learning,quantum reinforcement learning,and quantum deep *** an effort to address the limitations of smart cities,this article explores the formidable potential of quantum artificial intelligence in the realm of smart *** does so by examining aspects such as intelligent transportation,urban operation assurance,urban planning,and information communication,showcasing a plethora of practical achievements in the *** the foreseeable future,Quantum Artificial Intelligence(QAI)is poised to bring about revolutionary development to smart *** urgency lies in developing quantum artificial intelligence algorithms that are compatible with quantum computers,constructing an efficient,stable,and adaptive hybrid computing architecture that integrates quantum and classical computing,preparing quantum data as needed,and advancing controllable qubit hardware equipment to meet actual *** ultimate goal is to shape the next generation of artificial intelligence that possesses common sense cognitive abilities,robustness,excellent generalization capabilities,and interpretability.

关键词： quantum artificial intelligence smart city D-Wave quantum computer

来源：评论

学校读者我要写书评

暂无评论

Towards Lightweight Black-Box Attacks Against Deep Neural Networks 36

Towards Lightweight Black-Box Attacks Against Deep Neural Ne...

引用

36th Conference on Neural Information Processing Systems, NeurIPS 2022

作者： Sun, Chenghao Zhang, Yonggang Chaoqun, Wan Wang, Qizhou Li, Ya Liu, Tongliang Han, Bo Tian, Xinmei University of Science and Technology of China China Hong Kong Baptist University Hong Kong Alibaba Cloud Computing Ltd China iFlytek Research The University of Sydney Australia

ISBN: (纸本)9781713871088

Black-box attacks can generate adversarial examples without accessing the parameters of deep neural networks (DNNs), largely exacerbating the threats of deployed models. However, previous works state that black-box attacks fail to mislead DNNs when their training data and outputs are inaccessible. In this work, we argue that black-box attacks can pose practical attacks in this highly restrictive scenario where only several test samples are available. Specifically, we find that attacking the shallow layers of DNNs trained on a few test samples can generate powerful adversarial examples. As only a few samples are required, we refer to these attacks as lightweight black-box attacks. The main challenge to promoting lightweight attacks is to mitigate the adverse impact caused by the approximation error of shallow layers. As it is hard to mitigate the approximation error with few available samples, we propose Error TransFormer (ETF) for lightweight attacks. Namely, ETF transforms the approximation error in the parameter space into a perturbation in the feature space and alleviates the error by disturbing features. In our experiments, lightweight black-box attacks with the proposed ETF achieve surprising results. For example, even if only 1 sample per category is available, the attack success rate achieved by lightweight black-box attacks is only about 3% lower than that of the black-box attacks using complete training data. © 2022 Neural information processing systems foundation. All rights reserved.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

DAG-aware harmonizing job scheduling and data caching for disaggregated analytics frameworks

DAG-aware harmonizing job scheduling and data caching for di...

引用

作者： Tong, Yulai Liu, Jiazhen Wang, Hua He, Mingjian Zhou, Ke He, Rongfeng Zhang, Qin Wang, Cheng School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Wuhan National Laboratory for Optoelectronics Huazhong University of Science and Technology Wuhan430074 China Huawei Cloud Computing Technologies Co. Ltd Chengdu611730 China

Modern data analytics frameworks often integrate with external storage services, which can lead to storage bottlenecks. Existing caching and prefetching solutions utilize high-level information from data analytics frameworks to forecast future data accesses. They employ these predictions to prefetch data into the cache and manage the cache contents. However, this approach overlooks a fundamental opportunity: rather than caching data given a prediction of job execution, influencing the job execution order can enable more effective caching and prefetching. With this key insight, we introduce a novel system called TRIPOD, designed to synchronize job scheduling and data caching for analytics frameworks. Leveraging the higher-level information provided by analytics frameworks, TRIPOD explores the best-suited job execution order, guided by developed heuristics, to facilitate prefetching and caching. To fully exploit the potential of TRIPOD, we also introduce a novel caching strategy named CAP. This strategy not only acknowledges the job scheduling order but also offers fine-grained control over object prefetching and eviction. Our evaluation, conducted using standard analytic benchmarks (TPC-H and TPC-DS), demonstrates that TRIPOD achieves a speedup of up to 1.7x on state-of-the-art approaches. Moreover, when employing CAP to make caching decisions, the performance can further be improved (as much as 1.5x). © 2024

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Data Security Mining Method for Social Media Users’ Mental Health Status Test Based on Machine Learning Algorithm 3rd

Data Security Mining Method for Social Media Users’ Mental ...

引用

3rd EAI International Conference on IoT and Big Data Technologies for Health Care, IotCARE 2022

作者： Su, Junyu Liu, Wenjian Zhao, Hanxu Wang, Wennan Shi, Chiyu Faculty of Data Science City University of Macau China Alibaba Cloud Big Data Application College Zhuhai College of Science and Technology Zhuhai China Academy of Management Guangdong University of Science and Technology Dongguan China

ISBN: (纸本)9783031335440

Users who frequently use social media can easily lead to changes in their mental health status. In order to accurately predict users’ mental health status, a data mining method for testing social media users’ mental health status is designed based on machine learning algorithms. Perform clustering processing on the test data, calculate the centroid of each cluster and the sum of squared errors of the data set, and obtain the clustering result of the test data;extract the characteristics of social media users’ mental health status, and calculate the abnormal score of the object's mental health status, Use this to distinguish the user's psychological state;build a data mining model based on machine learning algorithms, build a one-dimensional convolutional neural network framework, record the activation functions of the convolutional layer and the pooling layer, and obtain the output value of the fully connected layer;design social media user psychology Health state test data analysis algorithm to obtain a safe mining method for social media users’ mental health state test data. Obtain the best period of social media users’ mental health status observation through experiments. It can be seen from the experimental data that the correlation of the mental health state mining results obtained by this method is higher than 0.91, and the prediction accuracy is higher than 92%, which improves the effectiveness of mental health state prediction. The best observation period is one month to two months before the expected time. © 2023, ICST Institute for Computer sciences, Social Informatics and Telecommunications Engineering.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

MoDAFold: a strategy for predicting the structure of missense mutant protein based on AlphaFold2 and molecular dynamics

引用

BRIEFINGS IN BIOINFORMATICS 2024年第2期25卷 bbae006-bbae006页

作者： Zheng, Lingyan Shi, Shuiyang Sun, Xiuna Lu, Mingkun Liao, Yang Zhu, Sisi Zhang, Hongning Pan, Ziqi Fang, Pan Zeng, Zhenyu Li, Honglin Li, Zhaorong Xue, Weiwei Zhu, Feng College of Pharmaceutical Sciences The Second Affiliated Hospital Zhejiang University School of Medicine Zhejiang University Hangzhou 310058 China Industry Solutions Research and Development Alibaba Cloud Computing Hangzhou 330110 China Key Laboratory of Elemene Class Anti-cancer Chinese Medicines School of Pharmacy Hangzhou Normal University Hangzhou 311121 China Innovation Institute for Artificial Intelligence in Medicine of Zhejiang University Alibaba-Zhejiang University Joint Research Center of Future Digital Healthcare Hangzhou 330110 China School of Pharmacy East China University of Science and Technology Shanghai 200237 China School of Pharmaceutical Sciences Chongqing University Chongqing 401331 China

Protein structure prediction is a longstanding issue crucial for identifying new drug targets and providing a mechanistic understanding of protein functions. To enhance the progress in this field, a spectrum of computational methodologies has been cultivated. AlphaFold2 has exhibited exceptional precision in predicting wild-type protein structures, with performance exceeding that of other methods. However, predicting the structures of missense mutant proteins using AlphaFold2 remains challenging due to the intricate and substantial structural alterations caused by minor sequence variations in the mutant proteins. Molecular dynamics (MD) has been validated for precisely capturing changes in amino acid interactions attributed to protein mutations. Therefore, for the first time, a strategy entitled 'MoDAFold' was proposed to improve the accuracy and reliability of missense mutant protein structure prediction by combining AlphaFold2 with MD. Multiple case studies have confirmed the superior performance of MoDAFold compared to other methods, particularly AlphaFold2.

关键词： MoDAFold missense mutant protein protein structure prediction deep learning molecular dynamics

来源：评论

学校读者我要写书评

暂无评论

The chordata olfactory receptor database

引用

Protein & Cell 2025年第4期16卷 283-292页

作者： Wei Han Siyu Bao Jintao Liu Yiran Wu Liting Zeng Tao Zhang Ningmeng Chen Kai Yao Shunguo Fan Aiping Huang Yuanyuan Feng Guiquan Zhang Ruiyi Zhang Hongjin Zhu Tian Hua Zhijie Liu Lina Cao Xingxu Huang Suwen Zhao Human Institute ShanghaiTech UniversityShanghai 201210China Research Center for Life Sciences Computing Zhejiang LabHangzhou 311121China Department of Intelligent Edge Cloud China Telecom Cloud Technology Co.Ltd.Shanghai 200120China School of Life Science and Technology ShanghaiTech UniversityShanghai 201210China School of Information Science and Technology Shanghai Tech UniversityShanghai 201210China Shanghai Key Laboratory of High-Resolution Electron Microscopy Shanghai Tech UniversityShanghai 201210China Zhejiang Provincial Key Laboratory of Pancreatic Disease The First Affiliated Hospitaland Institute of Translational MedicineZhejiang University School of MedicineHangzhou 310029China Shanghai Clinical Research and Trial Center Shanghai 201210China

Introduction of database Olfaction is one of the oldest chemosensory systems in chordates,playing crucial roles in their foraging,predator evasion,social communication,mating and parental care(Guo et al.,2023;Li and Liberles,2015;Liberles,2014).The initial step of olfaction is the binding and activation of olfactory receptors(ORs)by odorants in a combinatorial way(Malnic et al.,1999).

关键词： chordates chemosensory systems introduction database olfaction foraging olfaction binding activation olfactory olfactory receptors odorants

来源：评论

学校读者我要写书评

暂无评论

IMPROVING COMPLEX REASONING WITH DYNAMIC PROMPT CORRUPTION: A SOFT PROMPT OPTIMIZATION APPROACH

arXiv

引用

arXiv 2025年

作者： Fan, Sinan Xie, Liang Shen, Chen Teng, Ge Yuan, Xiaosong Zhang, Xiaofeng Huang, Chenxi Wang, Wenxiao He, Xiaofei Ye, Jieping Zhejiang University China Hangzhou YunQi Academy of Engineering China College of Computer Science and Technology Zhejiang University of Technology China Alibaba Cloud Computing China

Prompt-tuning (PT) for large language models (LLMs) can facilitate the performance on various conventional NLP tasks with significantly fewer trainable parameters. However, our investigation reveals that PT provides limited improvement and may even degrade the primitive performance of LLMs on complex reasoning tasks. Such a phenomenon suggests that soft prompts can positively impact certain instances while negatively affecting others, particularly during the later phases of reasoning. To address these challenges, We first identify an information accumulation within the soft prompts. Through detailed analysis, we demonstrate that this phenomenon is often accompanied by erroneous information flow patterns in the deeper layers of the model, which ultimately lead to incorrect reasoning outcomes. we propose a novel method called Dynamic Prompt Corruption (DPC) to take better advantage of soft prompts in complex reasoning tasks, which dynamically adjusts the influence of soft prompts based on their impact on the reasoning process. Specifically, DPC consists of two stages: Dynamic Trigger and Dynamic Corruption. First, Dynamic Trigger measures the impact of soft prompts, identifying whether beneficial or detrimental. Then, Dynamic Corruption mitigates the negative effects of soft prompts by selectively masking key tokens that interfere with the reasoning process. We validate the proposed approach through extensive experiments on various LLMs and reasoning tasks, including GSM8K, MATH, and AQuA. Experimental results demonstrate that DPC can consistently enhance the performance of PT, achieving 4%-8% accuracy gains compared to vanilla prompt tuning, highlighting the effectiveness of our approach and its potential to enhance complex reasoning in LLMs. © 2025, CC BY.

关键词： Modeling languages

来源：评论

学校读者我要写书评

暂无评论

Scaling Inter-procedural Dataflow Analysis on the cloud

arXiv

引用

arXiv 2024年

作者： Sun, Zewen Zhang, Yujin Xu, Duanchen Zhang, Yiyu Qi, Yun Wang, Yueyang Li, Yi Wang, Zhaokang Li, Yue Li, Xuandong Zuo, Zhiqiang Lu, Qingda Peng, Wenwen Guo, Shengjian State Key Laboratory for Novel Software Technology Nanjing University China Alibaba Cloud Computing United States Alibaba Cloud Computing China Baidu Research United States

Apart from forming the backbone of compiler optimization, static dataflow analysis has been widely applied in a vast variety of applications, such as bug detection, privacy analysis, program comprehension, etc. Despite its importance, performing interprocedural dataflow analysis on large-scale programs is well known to be challenging. In this paper, we propose a novel distributed analysis framework supporting the general interprocedural dataflow analysis. Inspired by large-scale graph processing, we devise dedicated distributed worklist algorithms for both whole-program analysis and incremental analysis. We implement these algorithms and develop a distributed framework called BigDataflow running on a large-scale cluster. The experimental results validate the promising performance of BigDataflow - BigDataflow can finish analyzing the program of millions lines of code in minutes. Compared with the state-of-the-art, BigDataflow achieves much more analysis efficiency. Copyright © 2024, The Authors. All rights reserved.

关键词： Data flow graphs

来源：评论

学校读者我要写书评

暂无评论

Introducing on-chain graph data to consortium blockchain for commercial transactions

引用

Frontiers of Computer science 2024年第2期18卷 255-257页

作者： Pengyi ZHANG Yuchen YUAN Jie SONG Yu GU Qiang QU Yongjie BAI Software College Northeastern UniversityShenyang 110819China School of Computer Science and Engineering Northeastern UniversityShenyang 110819China Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhen 518055China Blockchain Lab Huawei Cloud Computing Technologies Co.Ltd.Shenzhen 518101China

1 Introduction A blockchain can be referred to as a distributed ledger[1].Nowadays,according to our previous work[2],the graphrelated blockchain grows efficiently in both academic studies and commercial *** data,algor... 详细信息

关键词： transactions ledge commercial

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：