检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Zucchet, Nicolas Orvieto, Antonio Department of Computer Science ETH Zürich Switzerland ELLIS Institute Tübingen MPI for Intelligent Systems Tübingen AI Center Germany

Recurrent neural networks (RNNs) notoriously struggle to learn long-term memories, primarily due to vanishing and exploding gradients. The recent success of deep state-space models (SSMs), a subclass of RNNs, to overcome such difficulties challenges our theoretical understanding. In this paper, we delve into the optimization challenges of RNNs and discover that, as the memory of a network increases, changes in its parameters result in increasingly large output variations, making gradient-based learning highly sensitive, even without exploding gradients. Our analysis further reveals the importance of the element-wise recurrence design pattern combined with careful parametrizations in mitigating this effect. This feature is present in deep SSMs, as well as in other architectures, such as LSTMs. Overall, our insights provide a new explanation for some of the difficulties in gradient-based learning of RNNs and why some architectures perform better than others. Copyright © 2024, The Authors. All rights reserved.

关键词： State space methods

来源：评论

学校读者我要写书评

暂无评论

Proposal of a novel peeling of nano-particle (PNP) process for localized material removal on a hard material surface by controllable magnetic fields 22

Proposal of a novel peeling of nano-particle (PNP) process f...

引用

22nd International Conference of the European Society for Precision Engineering and Nanotechnology, EUSPEN 2022

作者： Permpatdechakul, Thitipat Khajornrungruang, Panart Suzuki, Keisuke Kutomi, Shotaro Graduate School of Computer Science and System Engineering Mechanical Information Science and Technology Course Kyushu Institute of Technology Fukuoka Japan Department of Intelligent and Control Systems Avanced Mechanical Division Kyushu Institute of Technology Fukuoka Japan School of Computer Science and System Engineering Advanced Mechanical Course Kyushu Institute of Technology Fukuoka Japan

ISBN: (纸本)9781998999118

This article proposes a novel Peeling of Nano-Particle (PNP) process to locally remove material on a hard material surface using controllable magnetic fields. Fe3O4 particles in the size range of 50-100 nm in aqueous solution (pH value 11 adjusted by KOH) were magnetically controlled to adhere and remove from a 4H-SiC surface by two electromagnetic coils, which were sandwiched between the substrate. The particle controlling phenomenon on the surface was experimentally observed and verified by our developed apparatus applying an evanescent field. According to the results, particles could be controlled to approach and remove from the substrate surface with 12mT of magnetic field at the selective area on the substrate surface to realise the proposed PNP process. © European Society for Precision Engineering and Nanotechnology, Conference Proceedings - 22nd International Conference and Exhibition, EUSPEN 2022. All rights reserved.

关键词： Magnetic fields

来源：评论

学校读者我要写书评

暂无评论

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Vehicle Designs 37

AircraftVerse: A Large-Scale Multimodal Dataset of Aerial Ve...

引用

37th Conference on Neural Information Processing systems, NeurIPS 2023

作者： Cobb, Adam D. Roy, Anirban Elenius, Daniel Heim, F. Michael Swenson, Brian Whittington, Sydney Walker, James D. Bapty, Theodore Hite, Joseph Ramani, Karthik McComb, Christopher Jha, Susmit Computer Science Laboratory SRI International United States Mechanical Engineering Division Southwest Research Institute United States Intelligent Systems Division Southwest Research Institute United States Institute of Software Integrated Systems Vanderbilt University United States School of Mechanical Engineering Purdue University United States Department of Mechanical Engineering Carnegie Mellon University United States

ISBN: (纸本)9781713899921

We present AircraftVerse, a publicly available aerial vehicle design dataset. Aircraft design encompasses different physics domains and, hence, multiple modalities of representation. The evaluation of these cyber-physical system (CPS) designs requires the use of scientific analytical and simulation models ranging from computer-aided design tools for structural and manufacturing analysis, computational fluid dynamics tools for drag and lift computation, battery models for energy estimation, and simulation models for flight control and dynamics. AircraftVerse contains 27, 714 diverse air vehicle designs - the largest corpus of engineering designs with this level of complexity. Each design comprises the following artifacts: a symbolic design tree describing topology, propulsion subsystem, battery subsystem, and other design details;a STandard for the Exchange of Product (STEP) model data;a 3D CAD design using a stereolithography (STL) file format;a 3D point cloud for the shape of the design;and evaluation results from high fidelity state-of-the-art physics models that characterize performance metrics such as maximum flight distance and hover-time. We also present baseline surrogate models that use different modalities of design representation to predict design performance metrics, which we provide as part of our dataset release. Finally, we discuss the potential impact of this dataset on the use of learning in aircraft design and, more generally, in CPS. AircraftVerse is accompanied by a data card, and it is released under Creative Commons Attribution-ShareAlike (CC BY-SA) license. The dataset is hosted at https://***/record/6525446, baseline models and code at https://***/SRI-CSL/AircraftVerse, and the dataset description at https://***/. © 2023 Neural information processing systems foundation. All rights reserved.

关键词： computer aided logic design

来源：评论

学校读者我要写书评

暂无评论

SELF-SUPERVISED VISUAL REINFORCEMENT LEARNING WITH OBJECT-CENTRIC REPRESENTATIONS 9

SELF-SUPERVISED VISUAL REINFORCEMENT LEARNING WITH OBJECT-CE...

引用

9th International Conference on Learning Representations, ICLR 2021

作者： Zadaianchuk, Andrii Seitzer, Maximilian Martius, Georg Max Planck Institute for Intelligent Systems Tübingen Germany Department of Computer Science ETH Zurich Switzerland

Autonomous agents need large repertoires of skills to act reasonably on new tasks that they have not seen before. However, acquiring these skills using only a stream of high-dimensional, unstructured, and unlabeled observations is a tricky challenge for any autonomous agent. Previous methods have used variational autoencoders to encode a scene into a low-dimensional vector that can be used as a goal for an agent to discover new skills. Nevertheless, in compositional/multiobject environments it is difficult to disentangle all the factors of variation into such a fixed-length representation of the whole scene. We propose to use object-centric representations as a modular and structured observation space, which is learned with a compositional generative world model. We show that the structure in the representations in combination with goal-conditioned attention policies helps the autonomous agent to discover and learn useful skills. These skills can be further combined to address compositional tasks like the manipulation of several different objects. https://***/SMORL. © 2021 ICLR 2021 - 9th International Conference on Learning Representations. All rights reserved.

关键词： Autonomous agents

来源：评论

学校读者我要写书评

暂无评论

Trust should correspond to trustworthiness: A formalization of appropriate mutual trust in human-agent teams 22

Trust should correspond to trustworthiness: A formalization ...

引用

22nd International Workshop on Trust in Agent Societies, TRUST 2021

作者： Jorge, Carolina Centeio Mehrotra, Siddharth Jonker, Catholijn M. Tielman, Myrthe L. Department of Intelligent Systems Tu Delft Netherlands Leiden Institute of Advanced Computer Science Leiden University Netherlands

In human-agent teams, how one teammate trusts another teammate should correspond to the latter's actual trustworthiness, creating what we would call appropriate mutual trust. Although this sounds obvious, the notion of appropriate mutual trust for human-agent teamwork lacks a formal definition. In this article, we propose a formalization which represents trust as a belief about trustworthiness. Then, we address mutual trust, and pose that agents can use beliefs about trustworthiness to represent how they trust their human teammates, as well as to reason about how their human teammates trust them. This gives us a formalization with nested beliefs about beliefs of trustworthiness. Next, we highlight that mutual trust should also be appropriate, where we define appropriate trust in an agent as the trust which corresponds directly to that agent's trustworthiness. Finally, we explore how agents can define their own trustworthiness, using the concepts of ability, benevolence and integrity. This formalization of appropriate mutual trust can form the base for developing agents which can promote such trust. © 2021 CEUR-WS. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heart Failure: Machine Learning Prediction Within a 5-Year Framework 24

Heart Failure: Machine Learning Prediction Within a 5-Year F...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Tsarapatsani, Konstantina-Helen Tsakanikas, Vasilios D. Sakellarios, Antonis Trampisch, Hans J. Karapintzou, Efterpi Rudolf, Henrik Matsopoulos, George K. Fotiadis, Dimitrios I. Biomedical Research Institute Foundation for Research and Technology-Hellas Ioannina Greece Ruhr University Bochum Department of Medical Informatics Biometry and Epidemiology Bochum Germany University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Greece Institute for Biostatistics and Informatics in Medicine and Ageing Research University Medical Center Rostock Germany School of Electrical and Computer Engineering National Technical University of Athens Athens Greece University of Ioannina and Biomedical Research Institute-FORTH Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering Ioannina Greece

ISBN: (纸本)9798331518622

Heart failure (HF) is a complex syndrome that is affected by many factors and causes. It is crucial to early recognize the disease subtypes and the unidentified clinical pathways that give rise to it. Machine learning (ML) is the tool that assist to deal with these challenges and improve the prediction of HF. In this work, the HF risk prediction was implemented by employed ML classifiers, such as Random Forest (RF), Extreme Grading Boosting (XGBoost) and Light Gradient-Boosting Machine (LGBM). We utilized the data from the German epidemiological trial on ankle brachial index - getABI cohort, which includes 6,454 patients. The performance of classifiers was estimated by Accuracy (ACC), Sensitivity, Specificity and the area under the receiver operating characteristic curve (AUC) in mean values for each ML classifier. The results were also interpreted using the Explainable artificial intelligence (XAI) approach, the Shapley Additive exPlanations (SHAP) values. Our work reveals that LGBM classifier predict the HF risk within 5 years follow-up in general population with 68 % accuracy. Moreover, the N-terminal pro-B-type natriuretic peptide (NT-proBNP) was identified as the most important feature for HF risk prediction. © 2024 IEEE.

关键词： Risk perception

来源：评论

学校读者我要写书评

暂无评论

CallNavi, A Challenge and Empirical Study on LLM Function Calling and Routing

arXiv

引用

arXiv 2025年

作者： Song, Yewei Tang, Xunzhu Lothritz, Cedric Ezzini, Saad Klein, Jacques Bissyandé, Tegawendé F. Boytsov, Andrey Ble, Ulrick Goujon, Anne University of Luxembourg Luxembourg Luxembourg Institute of Science and Technology Luxembourg Department of Information and Computer Science KFUPM Saudi Arabia BGL BNP PARIBAS Luxembourg Interdisciplinary Research Center for Intelligent Manufacturing and Robotics KFUPM Saudi Arabia

API-driven chatbot systems are increasingly integral to software engineering applications, yet their effectiveness hinges on accurately generating and executing API calls. This is particularly challenging in scenarios requiring multi-step interactions with complex parameterization and nested API dependencies. Addressing these challenges, this work contributes to the evaluation and assessment of AI-based software development through three key advancements: (1) the introduction of a novel dataset specifically designed for benchmarking API function selection, parameter generation, and nested API execution;(2) an empirical evaluation of state-of-the-art language models, analyzing their performance across varying task complexities in API function generation and parameter accuracy;and (3) a hybrid approach to API routing, combining general-purpose large language models for API selection with fine-tuned models and prompt engineering for parameter generation. These innovations significantly improve API execution in chatbot systems, offering practical methodologies for enhancing software design, testing, and operational workflows in real-world software engineering contexts. © 2025, CC BY-SA.

关键词： Software design

来源：评论

学校读者我要写书评

暂无评论

Sampling Strategies for Exploratory Landscape Analysis of Bi-Objective Problems

Sampling Strategies for Exploratory Landscape Analysis of Bi...

引用

2022 International Conference on Computational science and Computational Intelligence, CSCI 2022

作者： Kromer, Pavel Uher, Vojtech Andova, Andrejaana Tusar, Tea Filipic, Bogdan VSB - Technical University of Ostrava Department of Computer Science Ostrava-Poruba Czech Republic Jožef Stefan Institute Jožef Stefan International Postgraduate School Department of Intelligent Systems Ljubljana Slovenia

ISBN: (纸本)9798350320282

Exploratory landscape analysis (ELA) is a popular method for the understanding of complex, often black-box optimization problems. It tries to approximate and describe the surfaces formed by the fitness and other characteristic values associated with problem solutions on top of the multi-dimensional solution spaces. Sampling is the initial step of the ELA pipeline. It is a strategy for selecting a limited number of solutions, i.e., points in the multi-dimensional solution space, for which the fitness function(s) are evaluated. Consequently, the fitness landscape is approximated and its properties are drawn from these fitness values. In this work, the properties and the impact of various sampling strategies on the analysis of the fitness landscape are studied in the context of bi-objective optimization. Extensive computational experiments show that the use of different sampling strategies affects both the value of high-level landscape features and their usability for problem classification. The results also demonstrate that the magnitude and significance of the impact depend on problem dimension and sample size. © 2022 IEEE.

关键词： Optimization

来源：评论

学校读者我要写书评

暂无评论

Learnable Data Augmentation for One-Shot Unsupervised Domain Adaptation

arXiv

引用

arXiv 2023年

作者： Carrazco, Julio Ivan Davila Morerio, Pietro Del Bue, Alessio Murino, Vittorio Italian Institute of Technology Genoa Italy Department of Computer Science University of Verona Verona Italy Department of Computer Science and Technology Bioengineering Robotics and Systems Engineering University of Genova Genoa Italy Department of Marine Electrical Electronic and Telecommunications Engineering Robotics and Systems Engineering University of Genova Genoa Italy

This paper presents a classification framework based on learnable data augmentation to tackle the One-Shot Unsupervised Domain Adaptation (OS-UDA) problem. OS-UDA is the most challenging setting in Domain Adaptation, as only one single unlabeled target sample is assumed to be available for model adaptation. Driven by such single sample, our method LearnAug-UDA learns how to augment source data, making it perceptually similar to the target. As a result, a classifier trained on such augmented data will generalize well for the target domain. To achieve this, we designed an encoder-decoder architecture that exploits a perceptual loss and style transfer strategies to augment the source data. Our method achieves state-of-the-art performance on two well-known Domain Adaptation benchmarks, DomainNet and VisDA. The project code is available at https://***/IIT-PAVIS/LearnAug-UDA. © 2023, CC BY.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

BotScan: An Unsupervised Bot Detection Based on Adversarial Learning and Social Perception

BotScan: An Unsupervised Bot Detection Based on Adversarial ...

引用

Asian Control Conference

作者： Hong Lin Nuo Chen Yang Chen Xiang Li Cong Li Department of Electronic Engineering Adaptive Networks and Control Lab School of Information Science and Technology Fudan University China Shanghai Key Lab of Intelligent Information Processing School of Computer Science Fudan University China The Institute of Complex Networks and Intelligent Systems Shanghai Research Institute for Intelligent Autonomous Systems Tongji University China

ISBN: (数字)9789887581598

ISBN: (纸本)9798331540845

Within online social networks, the rapid expansion of automated accounts, known as social bots, poses a significant challenge. This dynamic has sparked a strategic contest between bots and detectors. Both sides continually learn and adjust their strategies to gain an edge in this silent war. To effectively manage risks from bot evolution, proactive detection methods have garnered widespread attention. In this work, we propose a graph-based and structure-aware adversarial learning framework for multi-category social bot detection. In detail, we adopt a categorical generative adversarial network to create synthetic evolved bot samples for adversarial learning, aiming to boost the detection performance. Besides, we design a user representation learning module, including local and remote feature extractors to mine neighborhood information and achieve multiple network structure representations. Results demonstrate that our model outperforms state-of-the-art approaches and exhibits strong robustness.

关键词： Representation learning Training Technological innovation Social networking (online) Image edge detection Detectors Feature extraction

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：