检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Theodore Papamarkou Maria Skoularidou Konstantina Palla Laurence Aitchison Julyan Arbel David Dunson Maurizio Filippone Vincent Fortuin Philipp Hennig José Miguel Hernández-Lobato Aliaksandr Hubin Alexander Immer Theofanis Karaletsos Mohammad Emtiyaz Khan Agustinus Kristiadi Yingzhen Li Stephan Mandt Christopher Nemeth Michael A. Osborne Tim G. J. Rudner David Rügamer Yee Whye Teh Max Welling Andrew Gordon Wilson Ruqi Zhang Department of Mathematics The University of Manchester Manchester UK Eric and Wendy Schmidt Center Broad Institute of MIT and Harvard Cambridge Spotify London UK Computational Neuroscience Unit University of Bristol Bristol UK Centre Inria de l'Université Grenoble Alpes Grenoble France Department of Statistical Science Duke University Statistics Program KAUST Saudi Arabia Helmholtz AI Munich Germany and Department of Computer Science Technical University of Munich Munich Germany and Munich Center for Machine Learning Munich Germany Tübingen AI Center University of Tübingen Tübingen Germany Department of Engineering University of Cambridge Cambridge UK Department of Mathematics University of Oslo Oslo Norway and Bioinformatics and Applied Statistics Norwegian University of Life Sciences Ås Norway Department of Computer Science ETH Zurich Switzerland Chan Zuckerberg Initiative California Center for Advanced Intelligence Project RIKEN Tokyo Japan Vector Institute Toronto Canada Department of Computing Imperial College London London UK Department of Computer Science UC Irvine Irvine Department of Mathematics and Statistics Lancaster University Lancaster UK Department of Engineering Science University of Oxford Oxford UK Center for Data Science New York University New York Munich Center for Machine Learning Munich Germany and Department of Statistics LMU Munich Munich Germany DeepMind London UK and Department of Statistics University of Oxford Oxford UK Informatics Institute University of Amsterdam Amsterdam Netherlands Courant Institute of Mathematical Sciences and Center for Data Science Computer Science Department New York University New York Department of Computer Science Purdue University West Lafayette

In the current landscape of deep learning research, there is a predominant emphasis on achieving high predictive accuracy in supervised tasks involving large image and language datasets. However, a broader perspective reveals a multitude of overlooked metrics, tasks, and data types, such as uncertainty, active and continual learning, and scientific data, that demand attention. Bayesian deep learning (BDL) constitutes a promising avenue, offering advantages across these diverse settings. This paper posits that BDL can elevate the capabilities of deep learning. It revisits the strengths of BDL, acknowledges existing challenges, and highlights some exciting research avenues aimed at addressing these obstacles. Looking ahead, the discussion focuses on possible ways to combine large-scale foundation models with BDL to unlock their full potential.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Malware Detection Method for Health Sensor Data Based on Machine Learning

A Malware Detection Method for Health Sensor Data Based on M...

引用

2020 IEEE International Conference on Informatics, IoT, and Enabling Technologies, ICIoT 2020

作者： Liu, Hanwen Helu, Xiaohan Jin, Chengjie Lu, Hui Tian, Zhihong Du, Xiaojiang Abualsaud, Khalid School of Computing National University of Singapore Department of Computer Science Singapore Singapore Cyberspace of Institute of Advanced Technology Guangzhou University Guangzhou China Temple University Department of Computer and Information Sciences Philadelphia United States College of Engineering Qatar University Department of Computer Science and Engfineering Qatar

ISBN: (纸本)9781728148212

Traditional signature-based malware detection approaches are sensitive to small changes in the malware code. Currently, most malware programs are adapted from existing programs. Hence, they share some common patterns but have different signatures. To health sensor data, it is necessary to identify the malware pattern rather than only detect the small changes. However, to detect these health sensor data in malware programs timely, we propose a fast detection strategy to detect the patterns in the code with machine learning-based approaches. In particular, XGBoost, LightGBM and Random Forests will be exploited in order to analyze the code from health sensor data. The codes are fed into them as sequences of bytes/tokens or just as a single byte/token (e.g. 1-, 2-, 3-, or 4-grams). Terabytes of program with labels, including benign and malware programs, have been collected. The challenges of this task are to select and get the features, modify the three models in order to train and test the dataset, which consists of health sensor data, and evaluate the features and models. When a malware program is detected by one model, its pattern will be broadcast to the other models, which will prevent malware program from intrusion effectively. © 2020 IEEE.

关键词： Health

来源：评论

学校读者我要写书评

暂无评论

Exploring the Advantages of Quantum Generative Adversarial Networks in Generative Chemistry

引用

Journal of Chemical Information and Modeling 2023年第11期63卷 3307-3318页

作者： Kao, Po-Yu Yang, Ya-Chu Chiang, Wei-Yin Hsiao, Jen-Yueh Cao, Yudong Aliper, Alex Ren, Feng Aspuru-Guzik, Alán Zhavoronkov, Alex Hsieh, Min-Hsiu Lin, Yen-Chu Insilico Medicine Taiwan Ltd. Taipei110208 Taiwan Research Institute Taipei114699 Taiwan Zapata Computing Inc. BostonMA02110 United States Insilico Medicine AI Limited Masdar City Abu Dhabi145748 United Arab Emirates Insilico Medicine Shanghai Ltd. Shanghai201203 China Department of Chemistry University of Toronto TorontoONM5S 3H6 Canada Department of Computer Science University of Toronto TorontoONM5S 2E4 Canada Vector Institute for Artificial Intelligence TorontoONM5S 1M1 Canada Lebovic Fellow Canadian Institute for Advanced Research TorontoONM5S 1M1 Canada Insilico Medicine Hong Kong Ltd. Hong Kong999077 Hong Kong Department of Pharmacy National Yang Ming Chiao Tung University Taipei112304 Taiwan

De novo drug design with desired biological activities is crucial for developing novel therapeutics for patients. The drug development process is time- and resource-consuming, and it has a low probability of success. Recent advances in machine learning and deep learning technology have reduced the time and cost of the discovery process and therefore, improved pharmaceutical research and development. In this paper, we explore the combination of two rapidly developing fields with lead candidate discovery in the drug development process. First, artificial intelligence has already been demonstrated to successfully accelerate conventional drug design approaches. Second, quantum computing has demonstrated promising potential in different applications, such as quantum chemistry, combinatorial optimizations, and machine learning. This article explores hybrid quantum-classical generative adversarial networks (GAN) for small molecule discovery. We substituted each element of GAN with a variational quantum circuit (VQC) and demonstrated the quantum advantages in the small drug discovery. Utilizing a VQC in the noise generator of a GAN to generate small molecules achieves better physicochemical properties and performance in the goal-directed benchmark than the classical counterpart. Moreover, we demonstrate the potential of a VQC with only tens of learnable parameters in the generator of GAN to generate small molecules. We also demonstrate the quantum advantage of a VQC in the discriminator of GAN. In this hybrid model, the number of learnable parameters is significantly less than the classical ones, and it can still generate valid molecules. The hybrid model with only tens of training parameters in the quantum discriminator outperforms the MLP-based one in terms of both generated molecule properties and the achieved KL divergence. However, the hybrid quantum-classical GANs still face challenges in generating unique and valid molecules compared to their classical counterparts.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Optimizing Low-Energy Carbon IIoT Systems with Quantum Algorithms: Performance Evaluation and Noise Robustness

arXiv

引用

arXiv 2025年

作者： Dave, Kshitij Innan, Nouhaila Behera, Bikash K. Mumtaz, Shahid Al-Kuwari, Saif Farouk, Ahmed Institute of Advanced Research Gandhinagar India Quantum Physics and Magnetism Team LPMC Faculty of Sciences Ben M’sick Hassan II University of Casablanca Morocco NYUAD Research Institute NYUAD Abu Dhabi United Arab Emirates Pvt. Ltd. WB Mohanpur741246 India Nottingham Trent University Engineering Department United Kingdom Qatar Center for Quantum Computing College of Science and Engineering Hamad Bin Khalifa University Doha Qatar Department of Computer Science Faculty of Computers and Artificial Intelligence Hurghada University Hurghada Egypt

Low-energy carbon Internet of Things (IoT) systems are essential for sustainable development, as they reduce carbon emissions while ensuring efficient device performance. Although classical algorithms manage energy efficiency and data processing within these systems, they often face scalability and real-time processing limitations. Quantum algorithms offer a solution to these challenges by delivering faster computations and improved optimization, thereby enhancing both the performance and sustainability of low-energy carbon IoT systems. Therefore, we introduced three quantum algorithms: quantum neural networks utilizing Pennylane (QNN-P), Qiskit (QNN-Q), and hybrid quantum neural networks (QNN-H). These algorithms are applied to two low-energy carbon IoT datasets—room occupancy detection (RODD) and GPS tracker (GPSD). For the RODD dataset, QNN-P achieved the highest accuracy at 0.95, followed by QNN-H at 0.91 and QNN-Q at 0.80. Similarly, for the GPSD dataset, QNN-P attained an accuracy of 0.94, QNN-H 0.87, and QNN-Q 0.74. Furthermore, the robustness of these models is verified against six noise models. The proposed quantum algorithms demonstrate superior computational efficiency and scalability in noisy environments, making them highly suitable for future low-energy carbon IoT systems. These advancements pave the way for more sustainable and efficient IoT infrastructures, significantly minimizing energy consumption while maintaining optimal device performance. © 2025, CC BY.

关键词： Low emission

来源：评论

学校读者我要写书评

暂无评论

Language-specific Characteristic Assistance for Code-switching Speech Recognition

arXiv

引用

arXiv 2022年

作者： Song, Tongtong Xu, Qiang Ge, Meng Wang, Longbiao Shi, Hao Lv, Yongjie Lin, Yuqin Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore Graduate School of Informatics Kyoto University Sakyo-ku Kyoto Japan Japan Advanced Institute of Science and Technology Ishikawa Japan

Dual-encoder structure successfully utilizes two language-specific encoders (LSEs) for code-switching speech recognition. Because LSEs are initialized by two pre-trained language-specific models (LSMs), the dual-encoder structure can exploit sufficient monolingual data and capture the individual language attributes. However, most existing methods have no language constraints on LSEs and underutilize language-specific knowledge of LSMs. In this paper, we propose a language-specific characteristic assistance (LSCA) method to mitigate the above problems. Specifically, during training, we introduce two language-specific losses as language constraints and generate corresponding language-specific targets for them. During decoding, we take the decoding abilities of LSMs into account by combining the output probabilities of two LSMs and the mixture model to obtain the final predictions. Experiments show that either the training or decoding method of LSCA can improve the model's performance. Furthermore, the best result can obtain up to 15.4% relative error reduction on the code-switching test set by combining the training and decoding methods of LSCA. Moreover, the system can process code-switching speech recognition tasks well without extra shared parameters or even retraining based on two pre-trained LSMs by using our method. Copyright © 2022, 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

Entanglement-efficient distributed quantum computing

Entanglement-efficient distributed quantum computing

引用

Quantum 2.0, QUANTUM 2024 in Quantum 2.0 Conference and Exhibition

作者： Wu, Jun-Yi Andres-Martinez, Pablo Forrer, Tim Mills, Daniel Matsui, Kosuke Henaut, Luciana Yamamoto, Kentaro Soeda, Akihito Duncan, Ross Murao, Mio Department of Physics Center for Advanced Quantum Computing Tamkang University New Taipei City25137 Taiwan Physics Division National Center for Theoretical Sciences Taipei10617 Taiwan Quantinuum Terrington House 13-15 Hills Road CambridgeCB2 1NL United Kingdom The University of Tokyo Hongo 7-3-1 Bunkyo-ku Tokyo113-0033 Japan National Institute of Informatics Chiyoda-ku Tokyo101-8430 Japan Department of Informatics SOKENDAI Chiyoda-ku Tokyo101-8430 Japan Department of Physics and Astronomy University College London Gower Street LondonWC1E 6BT United Kingdom Department of Computer and Information Sciences University of Strathclyde GlasgowG1 1XH United Kingdom Trans-scale Quantum Science Institute The University of Tokyo Bunkyo-ku Tokyo113-0033 Japan

We introduce an embedding-enhanced nonlocal-handling technique to save the entanglement consumption in distributed quantum computing (DQC) between two quantum processing units. The embedding technique is incorporated ... 详细信息

ISBN: (纸本)9781557525185

关键词： Quantum entanglement

来源：评论

学校读者我要写书评

暂无评论

Evaluating Machine Learning and Statistical Models for Greenland Subglacial Bed Topography

Evaluating Machine Learning and Statistical Models for Green...

引用

International Conference on Machine Learning and Applications (ICMLA)

作者： Katherine Yi Angelina Dewar Tartela Tabassum Jason Lu Ray Chen Homayra Alam Omar Faruque Sikan Li Mathieu Morlighem Jianwu Wang Department of Computer Science Purdue University West Lafayette IN USA Department of Physics University of Oregon Eugene OR USA Department of Information Systems University of Maryland Baltimore County Baltimore MD USA Department of Information Studies University of Maryland College Park College Park MD USA Marriotts Ridge High School Maryland Ellicott City MD USA Texas Advanced Computing Center University of Texas at Austin Austin TX USA Department of Earth Sciences Dartmouth College Hanover NH USA

The purpose of this research is to study how different machine learning and statistical models can be used to predict bedrock topography under the Greenland ice sheet using ice-penetrating radar and satellite imagery data. Accurate bed topography representations are crucial for understanding ice sheet stability and vulnerability to climate change. We explore nine predictive models including dense neural network, long-short term memory, variational auto-encoder, extreme gradient boosting (XGBoost), gaussian process regression, and kriging based residual learning. Model performance is evaluated with mean absolute error (MAE), root mean squared error (RMSE), coefficient of determination (R 2 ), and terrain ruggedness index (TRI). In addition to testing various models, different interpolation methods, including nearest neighbor, bilinear, and kriging, are also applied in preprocessing. The XGBoost model with kriging interpolation exhibit strong predictive capabilities but demands extensive resources. Alternatively, the XGBoost model with bilinear interpolation shows robust predictive capabilities and requires fewer resources. These models effectively capture the complexity of the terrain hidden under the Greenland ice sheet with precision and efficiency, making them valuable tools for representing spatial patterns in diverse landscapes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Neuromodulated Meta-Learning

arXiv

引用

arXiv 2024年

作者： Wang, Jingyao Guo, Huijie Qiang, Wenwen Li, Jiangmeng Zheng, Changwen Xiong, Hui Hua, Gang University of Chinese Academy of Sciences Beijing China National Key Laboratory of Space Integrated Information System Institute of Software Chinese Academy of Sciences Beijing China Beijing Advanced Innovation Center for Big Data and Brain Computing Beihang University Beijing China Thrust of Artificial Intelligence Hong Kong University of Science and Technology Guangzhou China Department of Computer Science and Engineering The Hong Kong University of Science and Technology Hong Kong Wormpex AI Research LLC BellevueWA98004 United States

Humans excel at adapting perceptions and actions to diverse environments, enabling efficient interaction with the external world. This adaptive capability relies on the biological nervous system (BNS), which activates different brain regions for distinct tasks. Meta-learning similarly trains machines to handle multiple tasks but relies on a fixed network structure, not as flexible as BNS. To investigate the role of flexible network structure (FNS) in meta-learning, we conduct extensive empirical and theoretical analyses, finding that model performance is tied to structure, with no universally optimal pattern across tasks. This reveals the crucial role of FNS in meta-learning, ensuring meta-learning to generate the optimal structure for each task, thereby maximizing the performance and learning efficiency of meta-learning. Motivated by this insight, we propose to define, measure, and model FNS in meta-learning. First, we define that an effective FNS should possess frugality, plasticity, and sensitivity. Then, to quantify FNS in practice, we present three measurements for these properties, collectively forming the structure constraint with theoretical supports. Building on this, we finally propose Neuromodulated Meta-Learning (NeuronML) to model FNS in meta-learning. It utilizes bi-level optimization to update both weights and structure with the structure constraint. Extensive theoretical and empirical evaluations demonstrate the effectiveness of NeuronML on various tasks. Code is publicly available at https://***/WangJingyao07/NeuronML. Copyright © 2024, The Authors. All rights reserved.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

DPER: Diffusion Prior Driven Neural Representation for Limited Angle and Sparse View CT Reconstruction

arXiv

引用

arXiv 2024年

作者： Du, Chenhe Lin, Xiyue Wu, Qing Tian, Xuanyu Su, Ying Luo, Zhe Zheng, Rui Chen, Yang Wei, Hongjiang Zhou, S. Kevin Yu, Jingyi Zhang, Yuyao The School of Information Science and Technology ShanghaiTech University Shanghai China The Department of Critical Care Medicine Zhongshan Hospital Fudan University Shanghai China The Laboratory of Image Science and Technology The School of Computer Science and Engineering The Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Southeast University Ministry of Education Nanjing210096 China The School of Biomedical Engineering Institute of Medical Robotics Shanghai Jiao Tong University Shanghai China School of Biomedical Engineering Suzhou Institute for Advanced Research University of Science and Technology of China Suzhou215123 China Institute of Computing Technology CAS Beijing100190 China

Limited-angle and sparse-view computed tomography (LACT and SVCT) are crucial for expanding the scope of X-ray CT applications. However, they face challenges due to incomplete data acquisition, resulting in diverse artifacts in the reconstructed CT images. Emerging implicit neural representation (INR) techniques, such as NeRF, NeAT, and NeRP, have shown promise in under-determined CT imaging reconstruction tasks. However, the unsupervised nature of INR architecture imposes limited constraints on the solution space, particularly for the highly ill-posed reconstruction task posed by LACT and ultra-SVCT. In this study, we introduce the Diffusion Prior Driven Neural Representation (DPER), an advanced unsupervised framework designed to address the exceptionally ill-posed CT reconstruction inverse problems. DPER adopts the Half Quadratic Splitting (HQS) algorithm to decompose the inverse problem into data fidelity and distribution prior sub-problems. The two sub-problems are respectively addressed by INR reconstruction scheme and pre-trained score-based diffusion model. This combination first injects the implicit image local consistency prior from INR. Additionally, it effectively augments the feasibility of the solution space for the inverse problem through the generative diffusion model, resulting in increased stability and precision in the solutions. We conduct comprehensive experiments to evaluate the performance of DPER on LACT and ultra-SVCT reconstruction with two public datasets (AAPM and LIDC), an in-house clinical COVID-19 dataset and a public raw projection dataset created by Mayo Clinic. The results show that our method outperforms the state-of-the-art reconstruction methods on in-domain datasets, while achieving significant performance improvements on out-of-domain (OOD) datasets. Copyright © 2024, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Improving the accuracy of circuit quantization using the electromagnetic properties of superconductors

arXiv

引用

arXiv 2024年

作者： Park, Seong Hyeon Choi, Gahyun Kim, Eunjong Park, Gwanyeol Choi, Jisoo Choi, Jiman Chong, Yonuk Lee, Yong-Ho Hahn, Seungyong Department of Electrical and Computer Engineering Seoul National University Seoul08826 Korea Republic of Center for Superconducting Quantum Computing Systems Korea Research Institute of Standards and Science Daejeon34113 Korea Republic of Department of Physics & Astronomy Institute of Applied Physics Seoul National University Seoul08826 Korea Republic of Quantum Devices Labs Korea Advanced Nano Fab Center Suwon16229 Korea Republic of Quantum Design Korea Seoul06272 Korea Republic of SKKU Adavanced Institute of Nanotechnology Sungkyunkwan University Suwon16419 Korea Republic of

Recent advances in quantum information processing with superconducting qubits have fueled a growing demand for scaling and miniaturizing circuit layouts. Despite significant progress, predicting the Hamiltonian of complex circuits remains a challenging task. Here, we propose an improved method for quantizing superconducting circuits that incorporates material- and geometry-dependent kinetic inductance. Our approach models superconducting films as reactive boundary elements, seamlessly integrating into the conventional circuit quantization framework without adding computational complexity. We experimentally validate our method using superconducting devices fabricated with 35 nm-thick disordered niobium films, demonstrating significantly improved accuracy in predicting the Hamiltonian based solely on the device layout and material properties of superconducting films and Josephson junctions. Specifically, conventional methods exhibit an average error of 5.4% in mode frequencies, while our method reduces it to 1.1%. Our method enables systematic studies of superconducting devices with disordered films or compact elements, facilitating precise engineering of superconducting circuits at scale. © 2024, CC BY-NC-ND.

关键词： Superconducting films

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：