检索结果-内蒙古大学图书馆

41st International Conference on Machine Learning, ICML 2024

作者： Wu, Anpeng Li, Haoxuan Kuang, Kun Zhang, Keli Wu, Fei Department of Computer Science and Technology Zhejiang University Hangzhou China Center for Data Science Peking University Beijing China Huawei Noah's Ark Lab Huawei Shenzhen China Shanghai Institute for Advanced Study Zhejiang University Shanghai China Shanghai AI Laboratory Shanghai China

This paper studies the causal relations from subsampled time series, in which measurements are sparse and sampled at a coarser timescale than the causal timescale of the underlying system. In such data, because there are numerous missing time-slices (i.e., cross-sections at each time point) between two consecutive measurements, conventional causal discovery methods designed for standard time series data would produce significant errors. To learn causal relations from subsampled time series, a typical solution is to conduct different interventions and then make a comparison. However, full interventions are often expensive, unethical, or even infeasible, particularly in fields such as health and social science. In this paper, we first explore how readily available two-time-slices data can replace intervention data to improve causal ordering, and propose a novel Descendant Hierarchical Topology algorithm with Conditional Independence Test (DHT-CIT) to learn causal relations from subsampled time series using only two time-slices. Specifically, we develop a conditional independence criterion that can be applied iteratively to test each node from time series and identify all of its descendant nodes. Empirical results on both synthetic and real-world datasets demonstrate the superiority of our DHT-CIT algorithm. Copyright 2024 by the author(s)

关键词： Time series analysis

来源：评论

学校读者我要写书评

暂无评论

I Can’t Share Code, but I need Translation - An Empirical Study on Code Translation through Federated LLM

arXiv

引用

arXiv 2025年

作者： Kumar, Jahnavi Janapati, Venkata Lakshmana Sasaank Tanguturi, Mokshith Reddy Chimalakonda, Sridhar Research in Intelligent Software & Human Analytics Lab Department of Computer Science and Engineering Indian Institute of Technology Tirupati India

Owing to the rapid evolution of technologies and project requirements, organizations need to upgrade the code base in their software projects to a new version of the programming language or even translating to an entirely new one. However, code translation is resource-intensive and requires expertise in both the source and target languages. While researchers have made progress in automating translations between legacy and modern languages, recent work has increasingly turned to pre-trained Large Language Models (LLMs) to translate efficiently. Given the proprietary nature of code, organizations prefer finetuning LLMs locally rather than relying on external APIs. This is one of the first empirical studies that proposes a Federated LLM-based approach for code translation. The proposed approach enables clients to jointly train a code translator without sharing sensitive data. This study demonstrates that participants can collaboratively develop a FedLLM for efficient code translation (particularly C# to Java and vice-versa) with superior results (more than 40% improvement in CodeLLaMA’s CodeBLEU score) compared to individual client models. Our findings indicate that FedLLM offers a collaborative approach to code translation and could serve as a promising direction for future research in this field. © 2025, CC BY.

关键词： Program translators

来源：评论

学校读者我要写书评

暂无评论

Applications of Machine Learning in Medicine: Current Trends and Prospects 6

Applications of Machine Learning in Medicine: Current Trends...

引用

6th Global Conference on Wireless and Optical Technologies, GCWOT 2023

作者： Aamir, Muhammad Bazai, Sibghatullah Bhatti, Uzair Aslam Dayo, Zaheer Ahmed Liu, Jing Zhang, Kun Huanggang Normal Univeristy College of Computer Science Huanggang China Balochistan University of Information Technology Engineering and Management Sciences Department of Computer Engineering Quetta Pakistan Hainan University School of Information and Communication Engineering Haikou China Zhejiang Lab Research Center for Healthcare Data Science Hangzhou China

ISBN: (纸本)9798350333718

With the continuous development of information technology and medical data information, more and more clinicians recognize artificial intelligence or will completely change medical practice by using advanced machine learning methods. The potential of using machine learning and predictive analysis to customize specific treatments for individuals is currently under research. Machine learning can learn a large number of medical data and explore the dependencies in data concentration, forming a corresponding medical model that can quickly and accurately predict new data, which is conducive to the early diagnosis of diseases and assisted clinical decisions. Clinical medicine faces the status quo of the relative shortage of medical resources and the identification and rapid diagnosis and treatment of critically ill emergency patients. In the era of big data, clinical demand is driven by clinical needs, and intelligent medical care provided by machines is the key to tackling the aforementioned issues. © 2023 IEEE.

关键词： Patient treatment

来源：评论

学校读者我要写书评

暂无评论

F-CNN: Faster CNN Exploiting Data Re-Use with Statistical Analysis 5

F-CNN: Faster CNN Exploiting Data Re-Use with Statistical An...

引用

5th IEEE International Conference on Artificial Intelligence Circuits and Systems, AICAS 2023

作者： Alantali, Fatmah Halawani, Yasmin Mohammad, Baker Al-Qutayri, Mahmoud Khalifa University System-on-Chip Lab Electrical Engineering and Computer Science Department Abu Dhabi United Arab Emirates University of Dubai College of Engineering & Information Technology Dubai United Arab Emirates

ISBN: (纸本)9798350332674

Many of the current edge computing devices need efficient implementation of Artificial Intelligence (AI) applications due to strict latency, security and power requirements. Nonetheless, such devices, face various challenges when executing AI applications due to their limited computing and energy resources. In particular, Convolutional Neural Networks (CNN) is a popular machine learning method that derives a high-level function from being trained on various visual input examples. This paper contributes to enabling the use of CNN on resource-constrained devices offline, where a trade-off between accuracy, running time and power efficiency is verified. The paper investigates the use of minimum pre-processing methods of input data to identify nonessential computations in the convolutional layers. In this work, Spatial locality of input data is considered along with an efficient pre-processing method to mitigate the accuracy loss caused by the computational re-use approach. This technique was tested on LeNet and CIFAR-10 structures and was responsible for 1.9% and 1.6% accuracy loss while reducing the processing time by 38.3% and 20.9% and reducing the energy by 38.3%, and 20.7%, respectively. The models were deployed and verified on Raspberry Pi 4 B platform using the MATlab coder to measure time and energy. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

GaussianEditor: Swift and Controllable 3D Editing with Gaussian Splatting

GaussianEditor: Swift and Controllable 3D Editing with Gauss...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Yiwen Chen Zilong Chen Chi Zhang Feng Wang Xiaofeng Yang Yikai Wang Zhongang Cai Lei Yang Huaping Liu Guosheng Lin S-Lab Nanyang Technological University School of Computer Science and Engineering Nanyang Technological University Department of Computer Science and Technology Tsinghua University Sense Time Research

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

3D editing plays a crucial role in many areas such as gaming and virtual reality. Traditional 3D editing methods, which rely on representations like meshes and point clouds, often fall short in realistically depicting complex scenes. On the other hand, methods based on implicit 3D representations, like Neural Radiance Field (NeRF), render complex scenes effectively but suffer from slow processing speeds and limited control over specific scene areas. In response to these challenges, our paper presents GaussianEditor, the first 3D editing algorithm based on Gaussian Splatting (GS), a novel 3D representation. GaussianEditor enhances precision and control in editing through our proposed Gaussian semantic tracing, which traces the editing target throughout the training process. Additionally, we propose Hierarchical Gaussian splatting (HGS) to achieve stabilized and fine results under stochastic generative guidance from 2D diffusion models. We also develop editing strategies for efficient object removal and integration, a challenging task for existing methods. Our comprehensive experiments demonstrate GaussianEditor's superior control, effective, and efficient performance, marking a significant advancement in 3D editing.

关键词： Training Point cloud compression Three-dimensional displays Semantics Stochastic processes Process control Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Empowering Healthcare Professionals and Patients with ChatGPT: Applications and Challenges

Empowering Healthcare Professionals and Patients with ChatGP...

引用

2023 Congress in computer science, computer Engineering, and Applied Computing, CSCE 2023

作者： Mosaiyebzadeh, Fatemeh Pouriyeh, Seyedamin Parizi, Reza M. Han, Meng Dehbozorgi, Nasrin Dorodchi, Mohsen Batista, Daniel MacÊdo University of São Paulo Department of Computer Science Brazil Kennesaw State University Department of Information and Technology MariettaGA United States Kennesaw State University Decentralized Science Lab MariettaGA United States Zhejiang University Zhejiang Hangzhou China Kennesaw State University Department of Software and Game Development MariettaGA United States Unc Charlotte Department of Computer Science Charlotte United States

ISBN: (纸本)9798350327595

ChatGPT is a recently developed Large Language Model (LLM) and an effective tool to produce human-like dialogue with users and answering to questions. It is trained on a massive amount of online content and can provide textual answers to questions from several domains, such as healthcare. In this paper, we investigate the application of ChatGPT in the healthcare domain and provide an analysis on its limitations and challenges. While ChatGPT can offer valuable support and information, it is crucial to recognize that it should not be seen as a replacement for the expertise and personalized care provided by healthcare professionals. Instead, its purpose lies in augmenting healthcare services and enhancing access to information. It can be a useful tool for providing general guidelines and educational resources. However, when it comes to medical advice or diagnosis, it is essential to consult qualified healthcare professionals who can consider individual factors, interpret complex medical information, and provide tailored recommendations based on a comprehensive understanding of the patient's situation. © 2023 IEEE.

关键词： Applications Artificial intelligence Challenges ChatGPT Healthcare

来源：评论

学校读者我要写书评

暂无评论

Artemis Removable-Canister Waste Accumulation System & Handler (ARC-WASH): A Portable Modular Space Lavatory

Artemis Removable-Canister Waste Accumulation System & Handl...

引用

2022 IEEE Aerospace Conference, AERO 2022

作者： Payra, Syamantak Paradiso, Joseph A. Massachusetts Institute of Technology Department of Electrical Engineering and Computer Science United States Responsive Environments Group Massachusetts Institute of Technology Mit Media Lab United States

ISBN: (数字)9781665437608

ISBN: (纸本)9781665437608

The Artemis Removable-Canister Waste Accumulation System and Handler (ARC-WASH) is a portable, modular space lavatory designed for use onboard spacecraft in both microgravity and terrestrial/lunar gravity. In designing this translunar waste collection and storage system, a systems engineering approach is combined with product design principles and inspiration from everyday objects to create a toilet that prioritizes crew comfort, inclusivity, and ease of use by all astronauts, while maintaining cleanliness, efficiency, and functionality in the most demanding of environments. The flexible, modular design of the ARC-WASH accommodates astronauts of all genders, solves problems faced with previous generations of space toilets, and introduces an unprecedented degree of versatility for use in landers, rovers, and even future space habitats. © 2022 IEEE.

关键词： Manned space flight

来源：评论

学校读者我要写书评

暂无评论

Profiling Irony and Stereotype Spreaders with Encoding Dependency Information using Graph Convolutional Network

Profiling Irony and Stereotype Spreaders with Encoding Depen...

引用

2022 Conference and labs of the Evaluation Forum, CLEF 2022

作者： Giglou, Hamed Babaei Rahgouy, Mostafa Rahmati, Ali Rahgooy, Taher Seals, Cheryl D. Department of Computer Science University of Tabriz Tabriz Iran Department of Computer Science Auburn University Alabama United States Algorithms Graphs Machine Learning Lab Amirkabir University of Technology Tehran Iran Department of Computer Science University of West Florida Florida United States Part AI Research Center Tehran Iran

Figurative language is using words in a way that deviates from the conventional order and meaning in order to ask the reader or listener to understand the meaning by virtue of its relation to some other meaning or concept. It is a rapidly growing area in Natural Language Processing, including the processing of irony, sarcasm, as well as other figures. With irony, language is employed in a figurative and subtle way to mean the opposite of what is literally stated. In this paper, we hypothesize that encoding dependency information allows us to find word associations that capture the author’s style where the main intent is to spread stereotypes in the form of irony. To do this end, we proposed a graph convolutional network that is able to learn the heterogeneous text graphs, representing various dependency information in the text, which enables classifiers to classify ironic and non-ironic spreaders via looking at heterogeneous features. Experimental results are very promising and show the effectiveness of our proposed method. © 2022 Copyright for this paper by its authors.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Generalizable Audio Deepfake Detection via Latent Space Refinement and Augmentation

Generalizable Audio Deepfake Detection via Latent Space Refi...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Wen Gu, Yanmei Wang, Zhiming Zhu, Huijia Qian, Yanmin Auditory Cognition and Computational Acoustics Lab MoE Key Lab of Artificial Intelligence AI Institute Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China SJTU Paris Elite Institute of Technology Shanghai China Ant Group Shanghai China

ISBN: (纸本)9798350368741

Advances in speech synthesis technologies, like text-to-speech (TTS) and voice conversion (VC), have made detecting deepfake speech increasingly challenging. Spoofing countermeasures often struggle to generalize effectively, particularly when faced with unseen attacks. To address this, we propose a novel strategy that integrates Latent Space Refinement (LSR) and Latent Space Augmentation (LSA) to improve the generalization of deepfake detection systems. LSR introduces multiple learnable prototypes for the spoof class, refining the latent space to better capture the intricate variations within spoofed data. LSA further diversifies spoofed data representations by applying augmentation techniques directly in the latent space, enabling the model to learn a broader range of spoofing patterns. We evaluated our approach on four representative datasets, i.e. ASVspoof 2019 LA, ASVspoof 2021 LA and DF, and In-The-Wild. The results show that LSR and LSA perform well individually, and their integration achieves competitive results, matching or surpassing current state-of-the-art methods. © 2025 IEEE.

关键词： anti-spoofing audio deepfake detection generalization

来源：评论

学校读者我要写书评

暂无评论

Corruption Robust Dynamic Pricing in Liner Shipping under Capacity Constraint

Corruption Robust Dynamic Pricing in Liner Shipping under Ca...

引用

International Conference on Data Engineering

作者： Yongyi Hu Xueyan Lit Xikai Wei Yangguang Shi Xiaofeng Gao Guihai Chen Department of Computer Science and Engineering MoE Key Lab of Artificial Intelligence Shanghai Jiao Tong University China School of Computer Science and Technology Shandong University China

ISBN: (数字)9798350317152

ISBN: (纸本)9798350317169

The shipping industry has irreplaceable importance in international trade and commerce. How to dynamically price different containers has long been a hot topic due to its direct connection to the final revenue. Two critical observations have been made after a comprehensive survey within a top liner company, China Ocean Shipping Company (COSCO). (1) Each type of container carried on a liner ship has its maximum capacity. (2) The sales volume is occasionally subject to huge fluctuations due to rare uncontrollable factors, such as COVID. Based on the above two points and the liner routine's periodic nature, we model the dynamic pricing problem as an episodic MDP model integrating with both capacity constraints and adversarial corruption, named C3-MDP. To maximize the cumulative revenue in the C3-MDP setting, we propose a programming framework, Bonus-Exploration based Episodic programming (BEEP). This framework can directly accommodate the linear programming algorithm to form the algorithm BEEP-LP, which provides the episode-wise greedy optimal strategy. Furthermore, a detailed regret analysis is provided, showing that BEEP-LP has a regret that is sublinear in the number of episodes. Combining deep techniques, we also present an approximation algorithm BEEP-DQN in the case of large state-action space to strike a balance between the running time and the performance. Abundant experiments based on real container sales data exhibit the rationality of C3-MDP and the effectiveness of BEEP.

关键词： Industries Surveys Pandemics Heuristic algorithms Oceans Pricing Companies

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：