检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Johnson, Samuel G.B. Karimi, Amir-Hossein Bengio, Yoshua Chater, Nick Gerstenberg, Tobias Larson, Kate Levine, Sydney Mitchell, Melanie Rahwan, Iyad Schölkopf, Bernhard Grossmann, Igor University of Waterloo Department of Psychology Canada University of Waterloo Department of Electrical and Computer Engineering Canada Université de Montréal Department of Computer Science and Operations Research Canada Warwick Business School Behavioural Science Group United Kingdom Stanford University Department of Psychology United States University of Waterloo Cheriton School of Computer Science Canada Allen Institute for Artificial Intelligence United States Santa Fe Institute United States Max Planck Institute for Human Development Germany Max Planck Institute for Intelligent Systems Germany

Recent advances in artificial intelligence (AI) have produced systems capable of increasingly sophisticated performance on cognitive tasks. However, AI systems still struggle in critical ways: unpredictable and novel environments (robustness), lack transparency in their reasoning (explainability), face challenges in communication and commitment (cooperation), and pose risks due to potential harmful actions (safety). We argue that these shortcomings stem from one overarching failure: AI systems lack wisdom. Drawing from cognitive and social sciences, we define wisdom as the ability to navigate intractable problems—those that are ambiguous, radically uncertain, novel, chaotic, or computationally explosive—through effective task-level and metacognitive strategies. While AI research has focused on task-level strategies, metacognition—the ability to reflect on and regulate one’s thought processes—is underdeveloped in AI systems. In humans, metacognitive strategies such as recognizing the limits of one’s knowledge, considering diverse perspectives, and adapting to context are essential for wise decision-making. We propose that integrating metacognitive capabilities into AI systems is crucial for enhancing their robustness, explainability, cooperation, and safety. By focusing on developing wise AI, we suggest an alternative to aligning AI with specific human values—a task fraught with conceptual and practical difficulties. Instead, wise AI systems can thoughtfully navigate complex situations, account for diverse human values, and avoid harmful actions. We discuss potential approaches to building wise AI, including benchmarking metacognitive abilities and training AI systems to employ wise reasoning. Prioritizing metacognition in AI research will lead to systems that act not only intelligently but also wisely in complex, real-world situations. © 2024, CC BY.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Research on Target Detection Method Based on Improved YOLOv5 19th

Research on Target Detection Method Based on Improved YOLOv5

引用

19th International Conference on Web Information systems and Applications, WISA 2022

作者： Wang, Rongzhuang Liu, Jun Zhang, Hualiang School of Computer Science and Technology Shenyang University of Chemical Technology Shenyang110142 China Liaoning Key Laboratory of Intelligent Technology for Chemical Process Industry Shenyang110142 China Key Laboratory of Networked Control Systems Chinese Academy of Sciences Shenyang110016 China Shenyang Institute of Automation Chinese Academy of Sciences Shenyang110016 China Institutes for Robotics and Intelligent Manufacturing Chinese Academy of Sciences Shenyang110169 China

ISBN: (纸本)9783031203084

At present, various target detection algorithms are used in detection and classification. It is a problem to improve the accuracy and speed of target detection by using deep learning and neural network model to train the parameters of the data set. Aiming at the problems of insufficient detection, inaccurate detection of complex background and loss of small target feature information in yolov5 target detection, an improved method combining hole convolution, moving exponential average and retraining of positive samples is proposed in this paper. This method effectively solves the problems of complex background, occlusion and incomplete feature extraction, reduces the loss rate of target features, and improves the detection accuracy of each category. The improved yolov5 target detection algorithm in this paper can not only use multi feature fusion and accelerate positive sample matching, but also use cavity convolution to increase receptive field, improve the detection effect of small targets and reduce the occurrence of missed detection and false detection. Experiments show that the improved yolov5 algorithm has better detection rate and lower loss rate than many existing target detection algorithms. © 2022, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Capacitor Minimization in Analog Synapses for Efficient and Compact Binarized SNNs

IEEE Transactions on Circuits and Systems for Artificial Int...

引用

IEEE Transactions on Circuits and systems for Artificial Intelligence 2025年第2期2卷 114-125页

作者： Mikail Yayla Ming-Liang Wei Simon Thomann Albi Mema Chia-Lin Yang Jian-Jia Chen Hussam Amrouch Design Automation for Embedded Systems Group TU Dortmund University Dortmund Germany Lamarr Institute for Machine Learning and Artificial Intelligence Dortmund Germany Department of the Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Technical University of Munich (TUM) Munich Germany TUM School of Computation Information and Technology Chair of AI Processor Design Munich Institute of Robotics and Machine Intelligence Munich Germany Department of Computer Science and Information Engineering Graduate Institute of Electronics Engineering National Taiwan University Taipei Taiwan Department of Computer Science TU Dortmund University Dortmund Germany Lamarr Institute Dortmund Germany

Accelerating the immense workloads of Neural Networks (NNs) is a critical challenge, and analog computing-based approaches present a promising solution. Among these, the Integrate-and-Fire (IF) Spiking Neural Network (SNN) stands out for its potential in efficient neural computation. However, achieving high inference accuracy through precise multiply-accumulate (MAC) operations necessitates a large membrane capacitor—224 to 547 times larger than the synapse array at the 14nm technology node—resulting in prohibitive area costs. Additionally, the large capacitor size introduces higher energy consumption and longer access times. Thus, a key research challenge is maintaining accuracy while mitigating the costs associated with the large membrane capacitor. In this work, we propose a HW/SW Codesign method, called CapMin, for capacitor size minimization in analog computing IF-SNNs. CapMin minimizes the capacitor size by reducing the number of spike times needed for accurate operation of the HW, based on the absolute frequency of MAC level occurrences in the SW. To increase the operation of IF-SNNs to current variation, we propose the method CapMin-V, which trades capacitor size for protection based on the reduced capacitor size found in CapMin. In our experiments, CapMin achieves more than a 14 $\times$ reduction in capacitor size along with a 34% reduction in energy consumption over the state of the art, while CapMin-V achieves increased variation tolerance in the IF-SNN operation, requiring only a small increase in capacitor size.

关键词： Capacitors Circuits Accuracy Capacitance Micromechanical devices Costs Neurons Integrated circuit modeling Spiking neural networks Hardware

来源：评论

学校读者我要写书评

暂无评论

Kronecker-Factored Approximate Curvature for Modern Neural Network Architectures

arXiv

引用

arXiv 2023年

作者： Eschenhagen, Runa Immer, Alexander Turner, Richard E. Schneider, Frank Hennig, Philipp University of Cambridge United Kingdom Department of Computer Science ETH Zurich Switzerland Max Planck Institute for Intelligent Systems Germany University of Tubingen Germany Tubingen AI Center Germany

The core components of many modern neural network architectures, such as transformers, convolutional, or graph neural networks, can be expressed as linear layers with weight-sharing. Kronecker-Factored Approximate Curvature (K-FAC), a second-order optimisation method, has shown promise to speed up neural network training and thereby reduce computational costs. However, there is currently no framework to apply it to generic architectures, specifically ones with linear weight-sharing layers. In this work, we identify two different settings of linear weight-sharing layers which motivate two flavours of K-FAC - expand and reduce. We show that they are exact for deep linear networks with weight-sharing in their respective setting. Notably, K-FAC-reduce is generally faster than K-FAC-expand, which we leverage to speed up automatic hyperparameter selection via optimising the marginal likelihood for a Wide ResNet. Finally, we observe little difference between these two K-FAC variations when using them to train both a graph neural network and a vision transformer. However, both variations are able to reach a fixed validation metric target in 50-75% of the number of steps of a first-order reference run, which translates into a comparable improvement in wall-clock time. This highlights the potential of applying K-FAC to modern neural network architectures. Copyright © 2023, The Authors. All rights reserved.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

A Closer Look on Gender Stereotypes in Movie Recommender systems and Their Implications with Privacy

arXiv

引用

arXiv 2025年

作者： Roy, Falguni Shen, Yiduo Zhao, Na Ding, Xiaofeng Faruk, Omar School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China Institute of Information Technology Noakhali Science and Technology University Sonapur Noakhali3814 Bangladesh Department of Computer Science Durham University DurhamDH1 3LE United Kingdom Institute for Intelligent Systems Research and Innovation Deakin University 75 Pigdons Rd Waurn PondsVIC3216 Australia

The movie recommender system typically leverages user feedback to provide personalized recommendations that align with user preferences and increase business revenue. This study investigates the impact of gender stereotypes on such systems through a specific attack scenario. In this scenario, an attacker determines users' gender-a private attribute-by exploiting gender stereotypes about movie preferences and analyzing users' feedback data, which is either publicly available or observed within the system. The study consists of two phases. In the first phase, a user study involving 630 participants identified gender stereotypes associated with movie genres, which often influence viewing choices. In the second phase, four inference algorithms were applied to detect gender stereotypes by combining the findings from the first phase with users' feedback data. Results showed that these algorithms performed more effectively than relying solely on feedback data for gender inference. Additionally, we quantified the extent of gender stereotypes to evaluate their broader impact on digital computational science. The latter part of the study utilized two major movie recommender datasets: MovieLens 1M and Yahoo!Movie. Detailed experimental information is available on our GitHub repository: https://***/friit/ *** © 2025, CC BY.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

The MatrixX solver for argumentation frameworks

arXiv

引用

arXiv 2021年

作者： Heinrich, Maximilian Intelligent Systems Department Computer Science Institute Leipzig University

MatrixX is a solver for Abstract Argumentation Frameworks. Offensive and defensive properties of an Argumentation Framework are notated in a matrix style. Rows and columns of this matrix are systematically reduced by the solver. This procedure is implemented through the use of hash maps in order to accelerate calculation time. MatrixX works for stable and complete semantics and was designed for the ICCMA'21 competition. © 2021, CC BY-NC-SA.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Proprioception and Tail Control Enable Extreme Terrain Traversal by Quadruped Robots

Proprioception and Tail Control Enable Extreme Terrain Trave...

引用

IEEE/RSJ International Conference on intelligent Robots and systems (IROS)

作者： Yanhao Yang Joseph Norby Justin K. Yim Aaron M. Johnson Department of Mechanical Engineering Carnegie Mellon University Pittsburgh PA USA Collaborative Robotics and Intelligent Systems Institute Oregon State University Corvallis OR USA Department of Mechanical Science and Engineering University of Illinois Urbana-Champaign Urbana IL USA

Legged robots leverage ground contacts and the reaction forces they provide to achieve agile locomotion. However, uncertainty coupled with contact discontinuities can lead to failure, especially in real-world environments with unexpected height variations such as rocky hills or curbs. To enable dynamic traversal of extreme terrain, this work introduces 1) a proprioception-based gait planner for estimating unknown hybrid events due to elevation changes and responding by modifying contact schedules and planned footholds online, and 2) a two-degree-of-freedom tail for improving contact-independent control and a corresponding decoupled control scheme for better versatility and efficiency. Simulation results show that the gait planner significantly improves stability under unforeseen terrain height changes compared to methods that assume fixed contact schedules and footholds. Further, tests have shown that the tail is particularly effective at maintaining stability when encountering a terrain change with an initial angular disturbance. The results show that these approaches work synergistically to stabilize locomotion with elevation changes up to 1.5 times the leg length and tilted initial states.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incomplete Gamma Kernels: Generalizing Locally Optimal Projection Operators

arXiv

引用

arXiv 2022年

作者： Stotko, Patrick Weinmann, Michael Klein, Reinhard Institute of Computer Science II – Visual Computing University of Bonn Germany Department of Intelligent Systems Delft University of Technology Netherlands

We present incomplete gamma kernels, a generalization of Locally Optimal Projection (LOP) operators. In particular, we reveal the relation of the classical localized L1 estimator, used in the LOP operator for point cloud denoising, to the common Mean Shift framework via a novel kernel. Furthermore, we generalize this result to a whole family of kernels that are built upon the incomplete gamma function and each represents a localized Lp estimator. By deriving various properties of the kernel family concerning distributional, Mean Shift induced, and other aspects such as strict positive definiteness, we obtain a deeper understanding of the operator’s projection behavior. From these theoretical insights, we illustrate several applications ranging from an improved Weighted LOP (WLOP) density weighting scheme and a more accurate Continuous LOP (CLOP) kernel approximation to the definition of a novel set of robust loss functions. These incomplete gamma losses include the Gaussian and LOP loss as special cases and can be applied to various tasks including normal filtering. Furthermore, we show that the novel kernels can be included as priors into neural networks. We demonstrate the effects of each application in a range of quantitative and qualitative experiments that highlight the benefits induced by our modifications. Copyright © 2022, The Authors. All rights reserved.

关键词： Normal distribution

来源：评论

学校读者我要写书评

暂无评论

Large-Scale Radiomics Analysis for Prostate Cancer Detection Harnessing Machine and Deep Learning Models 22

Large-Scale Radiomics Analysis for Prostate Cancer Detection...

引用

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Mylona, Eugenia Zaridis, Dimitrios I. Kalantzopoulos, Charalampos N. Pezoulas, Vasileios C. Tachos, Nikolaos S. Matsopoulos, George K. Regge, Daniele Papanikolaou, Nikolaos Tsiknakis, Manolis Marias, Kostas Fotiadis, Dimitrios I. Biomedical Research Institute Forth IoanninaGR 45110 Greece University of Ioannina Unit of Medical Technology Intelligent Information Systems Greece School of Electrical & Computer Engineering National Technical University of Athens Biomedical Engineering Laboratory Athens15780 Greece Candiolo Cancer Institute FPO-IRCCS Department of Radiology Strada Provinciale Candiolo Turin10060 Italy Champalimaud Foundation Computational Clinical Imaging Group Portugal Institute of Computer Science Forth Computational Biomedicine Laboratory HeraklionGR 70013 Greece Hellenic Mediterranean University Department of Electrical and Computer Engineering HeraklionGR 71004 Greece

ISBN: (纸本)9798331520526

Prostate cancer (PCa) is the second most common cancer in men, making early detection crucial for effective treatment. This study explores the efficacy of machine learning (ML) and deep learning (DL) models in detecting PCa lesions using radiomics features derived from multiparametric MRI data. Leveraging a dataset of 7621 retrospective and 2132 prospective cases from 12 clinical centers across Europe, we compared the performance of various ML (LASSO, Random Forest, SVM, XGBoost) and DL models (CNN, MLP, Transformer, CNN&MLP). Radiomic features were extracted and refined through a robust feature selection process. Models' performance was evaluated through nested cross-validation (CV) and externally. The CNN&MLP model achieved the highest ROC AUC (0.86) and PR AUC (0.90) in CV, while LASSO showed consistent generalization in external validation. Our findings indicate that DL models excel in high-dimensional data analysis but face challenges in generalizing to external datasets, highlighting the importance of external validation for clinical applicability. © 2025 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Applying Explanatory Artificial Intelligence Using LIME to Analyze Arabic Online Handwriting Recognition Models

Applying Explanatory Artificial Intelligence Using LIME to A...

引用

International Conference on Information Networking

作者： Hasanien Ali Talib Alothman Wafa Lejmi Safa Ameur Mohamed Ali Mahjoub ISITCom - Higher Institute of Computer Science and Communication Sousse Tunisia LATIS - Laboratory of Advanced Technology and Intelligent Systems National Engineering School of Sousse (ENISo) University of Sousse Sousse Tunisia Mechatronics Engineering Department University of Mosul Mosul Iraq

ISBN: (数字)9798331506940

ISBN: (纸本)9798331506957

This study applies interpretable artificial intelligence (XAI) techniques in an unprecedented way to improve transparency in online Arabic handwriting recognition models. By using the LIME (Local Model-Independent Explanations) technique to analyze and interpret a convolutional neural network (CNN) model trained on the ADAB dataset. LIME highlights the key features that the model relies on in handwriting recognition. This research demonstrates the effectiveness of the LIME technique in uncovering the factors that the model relies on in an unconventional way and provides detailed explanations of how the decisions are made, which enhances transparency and increases users’ confidence in these models. The results provide useful information for improving the performance of handwriting recognition systems and a beginning for applying XAI techniques on a larger scale, including using more complex datasets and additional interpretation techniques to gain a deeper understanding of how models work with different handwriting styles. This study paves the way for the use of interpretable techniques in the field of Arabic handwriting recognition.

关键词： Deep learning Handwriting recognition Analytical models Explainable AI Shape Decision making Predictive models Prediction algorithms Data models Convolutional neural networks

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：