检索结果-内蒙古大学图书馆

SSRN 2024年

作者： Schnake, Thomas Jafari, Farnoush Rezaei Lederer, Jonas Xiong, Ping Nakajima, Shinichi Gugler, Stefan Montavon, Grégoire Müller, Klaus-Robert Machine Learning Group Technical University of Berlin Berlin10623 Germany Berlin Institute for the Foundations of Learning and Data - BIFOLD Berlin10623 Germany RIKEN Saitama Wakō351-0198 Japan Department of Artificial Intelligence Korea University Seoul136-713 Korea Republic of Max Planck Institut für Informatik Saarbrücken66123 Germany Institute for Computer Science Free University of Berlin Berlin14195 Germany

Explainable Artificial Intelligence (XAI) plays a crucial role in fostering transparency and trust in AI systems, where traditional XAI approaches typically offer one level of abstraction for explanations, often in the form of heatmaps highlighting single or multiple input features. However, we ask whether abstract reasoning or problem-solving strategies of a model may also be relevant, as these align more closely with how humans approach solutions to problems. We propose a framework, called Symbolic XAI, that attributes relevance to symbolic queries expressing logical relationships between input features, thereby capturing the abstract reasoning behind a model’s predictions. The methodology is built upon a simple yet general multi-order decomposition of model predictions. This decomposition can be specified using higher-order propagation-based relevance methods, such as GNN-LRP, or perturbation-based explanation methods commonly used in XAI. The effectiveness of our framework is demonstrated in the domains of natural language processing (NLP), vision, and quantum chemistry (QC), where abstract symbolic domain knowledge is abundant and of significant interest to users. The Symbolic XAI framework provides an understanding of the model’s decision-making process that is both flexible for customization by the user and human-readable through logical formulas. © 2024, The Authors. All rights reserved.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

A Review of machine learning Algorithms for Detection of Breast Cancer

A Review of Machine Learning Algorithms for Detection of Bre...

引用

Ubiquitous Computing and Intelligent Information Systems (ICUIS), International Conference on

作者： Abhay Tale Aditya Barhate Prateek Verma Palash Gourshettiwar Department of Artificial Intelligence and Data Science Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Department of Artificial Intelligence and Machine Learning Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India Department of Computer Science and Medical Engineering Faculty of Engineering and Technology Datta Meghe Institute of Higher Education and Research (DU) Wardha Maharashtra India

ISBN: (数字)9798331529635

ISBN: (纸本)9798331529642

Breast cancer is still a global health concern, chiefly affecting women, as it is one of the major causes of cancer mortality. For the therapy to be effective, early diagnosis of cancer is critical to raising the survival level and increasing the effectiveness of the procedure. The advancement in the applied technique of machine learning (ML) has brought further opportunities for early and effective diagnosis of breast cancer. This review paper provides insights into how different ML algorithms including the Support Vector machine (SVM), Convolutional Neural Network (CNN), Random Forests, and many more have contributed to the detection of breast cancer. These algorithms have proved effective in providing solutions to various medical data and imaging including early diagnosis and treatment. The paper also looks at the use of ML with precision medicine to show that these technologies will help minimize false diagnoses and offer better treatment options. This review consolidates recent works and advancements to emphasize the prospect of ML in breast cancer management and calls for more studies to enhance its implementation in practice

关键词： Support vector machines machine learning algorithms Sensitivity Reviews Precision medicine Ubiquitous computing Breast cancer Vectors Convolutional neural networks Random forests

来源：评论

学校读者我要写书评

暂无评论

Corrected generalized cross-validation for finite ensembles of penalized estimators

arXiv

引用

arXiv 2023年

作者： Bellec, Pierre C. Du, Jin-Hong Koriyama, Takuya Patil, Pratik Tan, Kai Department of Statistics Rutgers University New BrunswickNJ08854 United States Department of Statistics and Data Science Carnegie Mellon University PittsburghPA15213 United States Machine Learning Department Carnegie Mellon University PittsburghPA15213 United States Department of Statistics University of California BerkeleyCA94720 United States

Generalized cross-validation (GCV) is a widely-used method for estimating the squared out-of-sample prediction risk that employs a scalar degrees of freedom adjustment (in a multiplicative sense) to the squared training error. In this paper, we examine the consistency of GCV for estimating the prediction risk of arbitrary ensembles of penalized least-squares estimators. We show that GCV is inconsistent for any finite ensemble of size greater than one. Towards repairing this shortcoming, we identify a correction that involves an additional scalar correction (in an additive sense) based on degrees of freedom adjusted training errors from each ensemble component. The proposed estimator (termed CGCV) maintains the computational advantages of GCV and requires neither sample splitting, model refitting, or out-of-bag risk estimation. The estimator stems from a finer inspection of the ensemble risk decomposition and two intermediate risk estimators for the components in this decomposition. We provide a non-asymptotic analysis of the CGCV and the two intermediate risk estimators for ensembles of convex penalized estimators under Gaussian features and a linear response model. Furthermore, in the special case of ridge regression, we extend the analysis to general feature and response distributions using random matrix theory, which establishes model-free uniform consistency of CGCV. Copyright © 2023, The Authors. All rights reserved.

关键词： Asymptotic analysis

来源：评论

学校读者我要写书评

暂无评论

Detection of Emergency Vehicles in Traffic and Assign Traffic Free Path Using Deep learning

Detection of Emergency Vehicles in Traffic and Assign Traffi...

引用

Sentiment Analysis and Deep learning (ICSADL), International Conference on

作者： Sriharsha Vikruthi Tejesh Reddy Singasani V T Ram Pavan Kumar M P V V S D Nagendrudu Ch Raghavendra R. Sahith Dept of CSE B V Raju Institute of Technology Narsapur Medak Telangana India University of Cumberlands Lousiville KY Dept of Computer Science Kakaraparti Bhavanarayana College Vijayawada Andhrapradesh India Department of Artificial Intelligence and Machine Learning Aditya Univeristy Suramplaem India Dept of CSE(Data Science) KKR & KSR Institute of Technology and Sciences Guntur Andhra Pradesh Dept of Computer Science and Engineering CVR College of Engineering Hyderabad Telangana India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Too much of Traffic jams are in a highly populated country. Sometimes emergency vehicles such as fire-fighter and ambulance get stuck in traffic, putting lives at threat in many cases. Priority should be given to special vehicles and their way should be cleared. However, traffic police find it difficult or sometimes impossible to handle with it. Emergency vehicles have visual and audio warning devices help them to overtake traffic by demanding as little space as possible from other vehicles. Many death happen due to delay in doctors, ambulance and fire engine vehicles while reaching their destinations. The traditional systems didn't provide path free route accurately. Therefore, by using detection of emergency vehicles in traffic and assign traffic free path using deep learning system, emergency vehicles can get free path or fast route by observing the traffic cameras. So, those emergency vehicles can reach the location on time by using RNN system. Therefore, the main objective is to improve this system for better results interms of accuracy, detection rate and precision.

关键词： Deep learning Space vehicles Visualization Sentiment analysis Recurrent neural networks Accuracy Law enforcement Roads Medical services Automobiles

来源：评论

学校读者我要写书评

暂无评论

learning Physics-Informed Neural Networks without Stacked Back-propagation

arXiv

引用

arXiv 2022年

作者： He, Di Li, Shanda Shi, Wenlei Gao, Xiaotian Zhang, Jia Bian, Jiang Wang, Liwei Liu, Tie-Yan National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University China Machine Learning Department School of Computer Science Carnegie Mellon University United States Microsoft Research Center for Data Science Peking University China

Physics-Informed Neural Network (PINN) has become a commonly used machine learning approach to solve partial differential equations (PDE). But, facing high-dimensional second-order PDE problems, PINN will suffer from severe scalability issues since its loss includes second-order derivatives, the computational cost of which will grow along with the dimension during stacked back-propagation. In this work, we develop a novel approach that can significantly accelerate the training of Physics-Informed Neural Networks. In particular, we parameterize the PDE solution by the Gaussian smoothed model and show that, derived from Stein's Identity, the second-order derivatives can be efficiently calculated without back-propagation. We further discuss the model capacity and provide variance reduction methods to address key limitations in the derivative estimation. Experimental results show that our proposed method can achieve competitive error compared to standard PINN training but is significantly faster. Our code is released at https://***/LithiumDA/PINN-without-Stacked-BP. Copyright © 2022, The Authors. All rights reserved.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

GSCLIP: A Framework for Explaining Distribution Shifts in Natural Language

arXiv

引用

arXiv 2022年

作者： Zhu, Zhiying Liang, Weixin Zou, James Department of Machine Learning Carnegie Mellon University PA United States Department of Computer Science Stanford University CA United States Department of Biomedical Data Science Stanford University CA United States Chan Zuckerberg Biohub San FranciscoCA United States

Helping end users comprehend the abstract distribution shifts can greatly facilitate AI deployment. Motivated by this, we propose a novel task, dataset explanation. Given two image data sets, dataset explanation aims to automatically point out their dataset-level distribution shifts with natural language. Current techniques for monitoring distribution shifts provide inadequate information to understand datasets with the goal of improving data quality. Therefore, we introduce GSCLIP, a training-free framework to solve the dataset explanation task. In GSCLIP, we propose the selector as the first quantitative evaluation method to identify explanations that are proper to summarize dataset shifts. Furthermore, we leverage this selector to demonstrate the superiority of a generator based on language model generation. Systematic evaluation on natural data shift verifies that GSCLIP, a combined system of a hybrid generator group and an efficient selector is not only easy-to-use but also powerful for dataset explanation at scale. Copyright © 2022, The Authors. All rights reserved.

关键词： machine learning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Alzheimer's Disease Diagnosis Using Multi-Relation Graph Convolutional Networks and Structural MRI data

Enhancing Alzheimer's Disease Diagnosis Using Multi-Relation...

引用

IoT Based Control Networks and Intelligent Systems (ICICNIS), International Conference on

作者： P. Rajesh Kanna C. Gunasundari M. Senthamarai P. Pandiaraja P. Nithin K. Chitra Department of Computer Science and Engineering Bannari Amman Institute of Technology Erode Tamil Nadu India Department of Computer Science and Engineering SRM Institute of Science and Technology Trichy Tamil Nadu India Department of Artificial Intelligence and Data Science Nandha Engineering College Erode Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Machine Learning Bannari Amman Institute of Technology Erode Tamil Nadu India Department of Computer Applications Kongu Engineering College Erode Tamil Nadu India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518103

Alzheimer's disease (AD) has substantial obstacles to early detection, which frequently leads to therapy delays. In this article a unique method that uses structural MRI data and Multi-Relation Graph Convolutional Networks (MR-GCN) to improve AD diagnostic accuracy. Which can capture the nuanced interactions that characterize neurodegenerative disorders by representing the intricate relationships between various brain regions as a multi-relational graph. This strategy provides a comprehensive picture of brain function and pathology through the combination of relational data and structural MRI features. Using a large dataset, the resusts are evaluated and contrasted in MR-GCN method with other machine-learning techniques and single-relation graph models. The findings demonstrate that this method outperforms current models in terms of classification accuracy and resilience, achieving higher sensitivity and specificity in distinguishing between individuals in good health and various stages of AD. Then for further exploration the interpretability of the model is identified in critical brain regions that support the diagnosing process. This work provides a promising framework for the integration of sophisticated graph-based medical imaging tools, which could lead to more sophisticated clinical applications in the diagnosis and monitoring of neurodegenerative diseases in addition to improving our understanding of how AD progresses.

关键词： Neuroimaging Pathology Accuracy Graph convolutional networks Magnetic resonance imaging machine learning Sensitivity and specificity Brain modeling Alzheimer's disease Resilience

来源：评论

学校读者我要写书评

暂无评论

Explainability and transparency in the realm of digital humanities: toward a historian XAI

引用

International Journal of Digital Humanities 2023年第2期5卷 299-331页

作者： El-Hajj, Hassan Eberle, Oliver Merklein, Anika Siebold, Anna Shlomi, Noga Büttner, Jochen Martinetz, Julius Müller, Klaus-Robert Montavon, Grégoire Valleriani, Matteo Max Planck Institute for the History of Science Berlin Germany BIFOLD – Berlin Institute for the Foundations of Learning and Data Berlin Germany Machine Learning Group Technische Universität Berlin Berlin Germany German Center for Art History Paris (DFK Paris) Paris France The Cohn Institute for the History and Philosophy of Science and Ideas Faculty of Humanities Tel-Aviv University Tel-Aviv Israel Department of Artificial Intelligence Korea University Seoul South Korea Max Planck Institute for Informatics Saarbrüken Germany Department of Mathematics and Computer Science Freie Universität Berlin Berlin Germany

The recent advancements in the field of Artificial Intelligence (AI) translated to an increased adoption of AI technology in the humanities, which is often challenged by the limited amount of annotated data, as well as its heterogeneity. Despite the scarcity of data it has become common practice to design increasingly complex AI models, usually at the expense of human readability, explainability, and trust. This in turn has led to an increased need for tools to help humanities scholars better explain and validate their models as well as their hypotheses. In this paper, we discuss the importance of employing Explainable AI (XAI) methods within the humanities to gain insights into historical processes as well as ensure model reproducibility and a trustworthy scientific result. To drive our point, we present several representative case studies from the Sphaera project where we analyze a large, well-curated corpus of early modern textbooks using an AI model, and rely on the XAI explanatory outputs to generate historical insights concerning their visual content. More specifically, we show that XAI can be used as a partner when investigating debated subjects in the history of science, such as what strategies were used in the early modern period to showcase mathematical instruments and machines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Spectral, Probabilistic, and Deep Metric learning: Tutorial and Survey

arXiv

引用

arXiv 2022年

作者： Ghojogh, Benyamin Ghodsi, Ali Karray, Fakhri Crowley, Mark Department of Electrical and Computer Engineering Machine Learning Laboratory University of Waterloo WaterlooON Canada Department of Statistics and Actuarial Science David R. Cheriton School of Computer Science Data Analytics Laboratory University of Waterloo WaterlooON Canada Department of Electrical and Computer Engineering Centre for Pattern Analysis and Machine Intelligence University of Waterloo WaterlooON Canada

This is a tutorial and survey paper on metric learning. Algorithms are divided into spectral, probabilistic, and deep metric learning. We first start with the definition of distance metric, Mahalanobis distance, and generalized Mahalanobis distance. In spectral methods, we start with methods using scatters of data, including the first spectral metric learning, relevant methods to Fisher discriminant analysis, Relevant Component Analysis (RCA), Discriminant Component Analysis (DCA), and the Fisher-HSIC method. Then, large-margin metric learning, imbalanced metric learning, locally linear metric adaptation, and adversarial metric learning are covered. We also explain several kernel spectral methods for metric learning in the feature space. We also introduce geometric metric learning methods on the Riemannian manifolds. In probabilistic methods, we start with collapsing classes in both input and feature spaces and then explain the neighborhood component analysis methods, Bayesian metric learning, information theoretic methods, and empirical risk minimization in metric learning. In deep learning methods, we first introduce reconstruction autoencoders and supervised loss functions for metric learning. Then, Siamese networks and its various loss functions, triplet mining, and triplet sampling are explained. Deep discriminant analysis methods, based on Fisher discriminant analysis, are also reviewed. Finally, we introduce multi-modal deep metric learning, geometric metric learning by neural networks, and few-shot metric learning. Copyright © 2022, The Authors. All rights reserved.

关键词： Surveys

来源：评论

学校读者我要写书评

暂无评论

Natural Language Processing in Virtual Assistants Current Approaches and Challenges

Natural Language Processing in Virtual Assistants Current Ap...

引用

science, Technology, Engineering and Management (ICSTEM), International Conference on

作者： Gautam Solaimalai J. Maria Shanthi Sampath Kumar S Priyanka Khabiya K. Geetha Gokul Talele US. Bank Software Engineering Manager Georgia United States of America Department of Artificial Intelligence and Machine Learning J B. Institute of Engineering and Technology Hyderabad Telangana India Department of Computer Science and Engineering Sri Eshwar College of Engineering Coimbatore Tamil Nadu India Department of Computer Science Engineering Mandsaur University Mandsaur Madhya Pradesh India Department of Computer Science G. T.N Arts College Dindigul Tamil Nadu India Department of Data Science Organization name Accenture Pune Maharashtra India

ISBN: (数字)9798350376913

ISBN: (纸本)9798350388473

The proliferation of virtual sidekicks in colorful disciplines has prodded a swell of interest in advancing Natural Language Processing(NLP) ways to enhance their effectiveness. This paper provides a comprehensive review of the current approaches and challenges encountered in integrating NLP into virtual sidekicks. It begins by outlining the foundational generalities of NLP and its vital part in enabling mortal- suchlike relations with virtual sidekicks. latterly, it delves into a discussion of the different methodologies employed in NLP for understanding and generating mortal language, ranging from rule-grounded systems to deep literacy models. likewise, the paper highlights the crucial challenges such as nebulosity resolution, environment understanding, and handling different verbal variations that stymie the flawless functioning of virtual sidekicks. By synthesizing perceptivity from recent exploration trials, this paper offers precious perspectives on the state-of-the-art NLP ways and directions for unborn exploration to overcome the challenges and propel the development of further intelligent and intuitive virtual sidekicks.

关键词： Reviews Virtual assistants Propulsion Natural language processing Distance measurement

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：