检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Li, Zhenshi Muhtar, Dilxat Gu, Feng Zhang, Xueliang Xiao, Pengfeng He, Guangjun Zhu, Xiaoxiang Jiangsu Provincial Key Laboratory of Geographic Information Science and Technology Nanjing210023 China Key Laboratory for Land Satellite Remote Sensing Applications of Ministry of Natural Resources Nanjing210023 China School of Geography and Ocean Science Nanjing University Nanjing210023 China Department of Aerospace and Geodesy Data Science in Earth Observation Technical University of Munich Bavaria Munich80333 Germany Munich Center for Machine Learning Bavaria Munich80333 Germany State Key Laboratory of Space-Ground Integrated Information Technology Beijing100095 China

Automatically and rapidly understanding Earth’s surface is fundamental to our grasp of the living environment and informed decision-making. This underscores the need for a unified system with comprehensive capabilities in analyzing Earth’s surface to address a wide range of human needs. The emergence of multimodal large language models (MLLMs) has great potential in boosting the efficiency and convenience of intelligent Earth observation. These models can engage in human-like conversations, serve as unified platforms for understanding images, follow diverse instructions, and provide insightful feedbacks. In this study, we introduce LHRS-Bot-Nova, an MLLM specialized in understanding remote sensing (RS) images, designed to expertly perform a wide range of RS understanding tasks aligned with human instructions. LHRS-Bot-Nova features an enhanced vision encoder and a novel bridge layer, enabling efficient visual compression and better language-vision alignment. To further enhance RS-oriented vision-language alignment, we propose a large-scale RS image-caption dataset, generated through feature-guided image recaptioning. Additionally, we introduce an instruction dataset specifically designed to improve spatial recognition abilities. Extensive experiments demonstrate superior performance of LHRS-Bot-Nova across various RS image understanding tasks. We also evaluate different MLLM performances in complex RS perception and instruction following using a complicated multi-choice question evaluation benchmark, providing a reliable guide for future model selection and improvement. data, code, and models will be available at https://***/NJU-LHRS/LHRS-Bot. Copyright © 2024, The Authors. All rights reserved.

关键词： Visual languages

来源：评论

学校读者我要写书评

暂无评论

Uniform-in-Time Wasserstein Stability Bounds for (Noisy) Stochastic Gradient Descent

arXiv

引用

arXiv 2023年

作者： Zhu, Lingjiong Gürbüzbalaban, Mert Raj, Anant Şimşekli, Umut Department of Mathematics Florida State University TallahasseeFL United States Department of Management Science and Information Systems Rutgers Business School PiscatawayNJ United States Center for Statistics and Machine Learning Princeton University PrincetonNJ United States Coordinated Science Laboraotry University of Illinois Urbana-ChampaignIL United States Inria Ecole Normale Supérieure PSL Research University Paris France Inria CNRS Ecole Normale Supérieure PSL Research University Paris France

Algorithmic stability is an important notion that has proven powerful for deriving generalization bounds for practical algorithms. The last decade has witnessed an increasing number of stability bounds for different algorithms applied on different classes of loss functions. While these bounds have illuminated various properties of optimization algorithms, the analysis of each case typically required a different proof technique with significantly different mathematical tools. In this study, we make a novel connection between learning theory and applied probability and introduce a unified guideline for proving Wasserstein stability bounds for stochastic optimization algorithms. We illustrate our approach on stochastic gradient descent (SGD) and we obtain time-uniform stability bounds (i.e., the bound does not increase with the number of iterations) for strongly convex losses and nonconvex losses with additive noise, where we recover similar results to the prior art or extend them to more general cases by using a single proof technique. Our approach is flexible and can be generalizable to other popular optimizers, as it mainly requires developing Lyapunov functions, which are often readily available in the literature. It also illustrates that ergodicity is an important component for obtaining time-uniform bounds - which might not be achieved for convex or non-convex losses unless additional noise is injected to the iterates. Finally, we slightly stretch our analysis technique and prove time-uniform bounds for SGD under convex and non-convex losses (without additional additive noise), which, to our knowledge, is novel. Copyright © 2023, The Authors. All rights reserved.

关键词： Additive noise

来源：评论

学校读者我要写书评

暂无评论

Is L2 physics-informed loss always suitable for training physics-informed neural network? 22

Is L2 physics-informed loss always suitable for training phy...

引用

Proceedings of the 36th International Conference on Neural Information Processing Systems

作者： Chuwei Wang Shanda Li Di He Liwei Wang School of Mathematical Sciences Peking University Machine Learning Department School of Computer Science Carnegie Mellon University and Zhejiang Lab National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University National Key Laboratory of General Artificial Intelligence School of Intelligence Science and Technology Peking University and Center for Data Science Peking University

ISBN: (纸本)9781713871088

The Physics-Informed Neural Network (PINN) approach is a new and promising way to solve partial differential equations using deep learning. The L2 Physics- Informed Loss is the de-facto standard in training Physics-Informed Neural Networks. In this paper, we challenge this common practice by investigating the relationship between the loss function and the approximation quality of the learned solution. In particular, we leverage the concept of stability in the literature of partial differential equation to study the asymptotic behavior of the learned solution as the loss approaches zero. With this concept, we study an important class of high-dimensional non-linear PDEs in optimal control, the Hamilton-Jacobi- Bellman (HJB) Equation, and prove that for general Lp Physics-Informed Loss, a wide class of HJB equation is stable only if p is sufficiently large. Therefore, the commonly used L2 loss is not suitable for training PINN on those equations, while L∞ loss is a better choice. Based on the theoretical insight, we develop a novel PINN training algorithm to minimize the L∞ loss for HJB equations which is in a similar spirit to adversarial training. The effectiveness of the proposed algorithm is empirically demonstrated through experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Physics-aware machine learning Revolutionizes Scientific Paradigm for machine learning and Process-based Hydrology

arXiv

引用

arXiv 2023年

作者： Xu, Qingsong Shi, Yilei Bamber, Jonathan Tuo, Ye Ludwig, Ralf Zhu, Xiao Xiang Data Science in Earth Observation Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany School of Engineering and Design Technical University of Munich Munich Germany Hydrology and River Basin Management Technical University of Munich Munich Germany Department of Geography Ludwig-Maximilians-University Munich Germany School of Geographical Sciences University of Bristol United Kingdom

Accurate geoscientific process understanding and water cycle prediction are crucial for addressing scientific and societal challenges associated with the management of water resources. Existing reviews predominantly concentrate on the development of machine learning (ML) in this field, yet there is a clear distinction between process-based hydrology and ML as separate paradigms. Here, we introduce physics-aware ML as a transformative approach to overcome the perceived barrier and revolutionize both fields. Specifically, we present a comprehensive review of the physics-aware ML methods, building a structured community (PaML) of existing methodologies that integrate prior physical knowledge or physics-based modeling into ML. We systematically analyze these PaML methodologies with respect to four aspects: physical data-guided ML, physics-informed ML, physics-embedded ML, and physics-aware hybrid learning. PaML facilitates ML-aided hypotheses, accelerating insights from big data and fostering scientific discoveries. We first conduct a systematic review of hydrology in PaML, including rainfall-runoff hydrological processes and hydrodynamic processes, and highlight the most promising and challenging directions for different objectives and PaML methods. Finally, a new PaML-based hydrology platform, termed HydroPML, is released as a foundation for hydrological applications. HydroPML enhances the explainability and causality of ML and lays the groundwork for the digital water cycle’s realization. The HydroPML platform is publicly available at https://***/. Copyright © 2023, The Authors. All rights reserved.

关键词： Runoff

来源：评论

学校读者我要写书评

暂无评论

A systematic review of machine learning-based tumor-infiltrating lymphocytes analysis in colorectal cancer: Overview of techniques, performance metrics, and clinical outcomes

引用

Computers in Biology and Medicine 2024年 173卷 108306-108306页

作者： Kazemi, Azar Rasouli-Saravani, Ashkan Gharib, Masoumeh Albuquerque, Tomé Eslami, Saeid Schüffler, Peter J. Department of Medical Informatics School of Medicine Mashhad University of Medical Sciences Mashhad Iran Institute of General and Surgical Pathology Technical University of Munich Munich Germany Student Research Committee Department of Immunology School of Medicine Shahid Beheshti University of Medical Sciences Tehran Iran Department of Pathology Faculty of Medicine Mashhad University of Medical Sciences Mashhad Iran INESC TEC -Rua Dr. Roberto Frias Porto Portugal Pharmaceutical Sciences Research Center Institute of Pharmaceutical Technology Mashhad University of Medical Sciences Mashhad Iran Department of Medical Informatics University of Amsterdam Amsterdam Netherlands TUM School of Computation Information and Technology Technical University of Munich Munich Germany Munich Center for Machine Learning Munich Germany Munich Data Science Institute Munich Germany

The incidence of colorectal cancer (CRC), one of the deadliest cancers around the world, is increasing. Tissue microenvironment (TME) features such as tumor-infiltrating lymphocytes (TILs) can have a crucial impact on diagnosis or decision-making for treating patients with CRC. While clinical studies showed that TILs improve the host immune response, leading to a better prognosis, inter-observer agreement for quantifying TILs is not perfect. Incorporating machine learning (ML) based applications in clinical routine may promote diagnosis reliability. Recently, ML has shown potential for making progress in routine clinical procedures. We aim to systematically review the TILs analysis based on ML in CRC histological images. Deep learning (DL) and non-DL techniques can aid pathologists in identifying TILs, and automated TILs are associated with patient outcomes. However, a large multi-institutional CRC dataset with a diverse and multi-ethnic population is necessary to generalize ML methods. © 2024 Elsevier Ltd

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Vision-Language Models in Remote Sensing: Current Progress and Future Trends

arXiv

引用

arXiv 2023年

作者： Li, Xiang Wen, Congcong Hu, Yuan Yuan, Zhenghang Zhu, Xiao Xiang The King Abdullah University of Science and Technology Thuwal23955 Saudi Arabia Department of Electrical and Computer Engineering New York University Abu Dhabi Abu Dhabi129188 United Arab Emirates The Institute of Remote Sensing and Geographic Information Systems Peking University Beijing100871 China Data Science in Earth Observation Technical University of Munich Munich80333 Germany The Munich Center for Machine Learning Munich80333 Germany

The remarkable achievements of ChatGPT and GPT-4 have sparked a wave of interest and research in the field of large language models for Artificial General Intelligence (AGI). These models provide intelligent solutions close to human thinking, enabling us to use general artificial intelligence to solve problems in various applications. However, in remote sensing (RS), the scientific literature on the implementation of AGI remains relatively scant. Existing AI-related research in remote sensing primarily focuses on visual understanding tasks while neglecting the semantic understanding of the objects and their relationships. This is where vision-language models excel, as they enable reasoning about images and their associated textual descriptions, allowing for a deeper understanding of the underlying semantics. Vision-language models can go beyond visual recognition of RS images, model semantic relationships, and generate natural language descriptions of the image. This makes them better suited for tasks requiring visual and textual understanding, such as image captioning, and visual question answering. This paper provides a comprehensive review of the research on vision-language models in remote sensing, summarizing the latest progress, highlighting challenges, and identifying potential research opportunities. Specifically, we review the application of vision-language models in mainstream remote sensing tasks, including image captioning, text-based image generation, text-based image retrieval, visual question answering, scene classification, semantic segmentation, and object detection. For each task, we analyze representative works and discuss research progress. We also summarize the commonly used remote sensing vision-language datasets, codebases, and online accessible resources. Finally, we delineate the limitations of current studies and suggest potential avenues for future advancements. This review aims to provide a comprehensive review of the current research pro

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Exploring the Capabilities of a Language Model-Only Approach for Depression Detection in Text data

Exploring the Capabilities of a Language Model-Only Approach...

引用

IEEE EMBS International Conference on Information Technology Applications in Biomedicine (ITAB)

作者： Misha Sadeghi Bernhard Egger Reza Agahi Robert Richer Klara Capito Lydia Helene Rupp Lena Schindler-Gmelch Matthias Berking Bjoern M. Eskofier Department Artificial Intelligence in Biomedical Engineering Machine Learning and Data Analytics Lab Friedrich-Alexander-Universität Erlangen- Nürnberg (FAU) Erlangen Germany Department of Computer Science Chair of Visual Computing Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany Syenah GMBH Eschborn Germany Chair of Clinical Psychology and Psychotherapy Friedrich-Alexander-Universität Erlangen-Nürnberg (FAU) Erlangen Germany

Depression is a prevalent and debilitating mental health condition that requires accurate and efficient detection for timely and effective treatment. In this study, we utilized the E-DAIC (Extended Distress Analysis Interview Corpus-Wizard-of-Oz) dataset, an extended version of the DAIC-WOZ dataset, which consists of semi-clinical interviews conducted by an animated virtual interviewer called Ellie, controlled by a human interviewer in another room. With 275 participants, the E-DAIC dataset represents a valuable resource for investigating depression detection methods. Our aim is to predict PHQ-8 scores through text analysis. Leveraging state-of-the-art speech processing, LLM-based text summarization, and a specialized depression detection module, we demonstrate the transformative potential of language data analysis in enhancing depression screening. By overcoming the limitations of manual feature extraction methods, our automated techniques provide a more efficient and effective means of evaluating depression. In our evaluation, we achieve robust accuracy on the development set of the E-DAIC dataset, with a Mean Absolute Error (MAE) of 3.65 in estimating PHQ-8 scores from recorded interviews. This remarkable performance highlights the efficacy of our approach in automatically predicting depression severity. Our research contributes to the growing evidence supporting the use of LLMs in mental health assessment, showcasing the role of innovative technologies in advancing patient care for depression.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Understanding the generalization of Adam in learning neural networks with proper regularization

arXiv

引用

arXiv 2021年

作者： Zou, Difan Cao, Yuan Li, Yuanzhi Gu, Quanquan Department of Computer Science University of California Los AngelesCA United States Department of Statistics and Actuarial Science Department of Mathematics The University of Hong Kong Hong Kong Machine Learning Department Carnegie Mellon University PittsburghPA United States Department of Computer Science University of California Los AngelesCA United States

Adaptive gradient methods such as Adam have gained increasing popularity in deep learning optimization. However, it has been observed that compared with (stochastic) gradient descent, Adam can converge to a different solution with a significantly worse test error in many deep learning applications such as image classification, even with a fine-tuned regularization. In this paper, we provide a theoretical explanation for this phenomenon: we show that in the nonconvex setting of learning over-parameterized two-layer convolutional neural networks starting from the same random initialization, for a class of data distributions (inspired from image data), Adam and gradient descent (GD) can converge to different global solutions of the training objective with provably different generalization errors, even with weight decay regularization. In contrast, we show that if the training objective is convex, and the weight decay regularization is employed, any optimization algorithms including Adam and GD will converge to the same solution if the training is successful. This suggests that the inferior generalization performance of Adam is fundamentally tied to the nonconvex landscape of deep learning optimization. Copyright © 2021, The Authors. All rights reserved.

关键词： Gradient methods

来源：评论

学校读者我要写书评

暂无评论

Parameter estimation for cellular automata

arXiv

引用

arXiv 2023年

作者： Kazarnikov, Alexey Ray, Nadja Haario, Heikki Lappalainen, Joona Rupp, Andreas Heidelberg University Mathematikon Im Neuenheimer Feld 205 Heidelberg69120 Germany Mathematical Institute for Machine Learning and Data Science Catholic University of Eichstätt-Ingolstadt Hohe-Schul-Str. 5 Ingolstadt85049 Germany School of Engineering Science Lappeenranta–Lahti University of Technology P.O. Box 20 Lappeenranta53851 Finland Department of Mathematics Faculty of Mathematics and Computer Science Saarland University SaarbrückenDE-66123 Germany

Self-organizing complex systems can be modeled using cellular automaton models. However, the parametrization of these models is crucial and significantly determines the resulting structural pattern. In this research, we introduce and successfully apply a sound statistical method to estimate these parameters. The decisive difference to earlier applications of such approaches is that, in our case, both the CA rules and the resulting patterns are discrete. The method is based on constructing Gaussian likelihoods using characteristics of the structures, such as the mean particle size. We show that our approach is robust for the method parameters, domain size of patterns, or CA iterations. Copyright © 2023, The Authors. All rights reserved.

关键词： Statistical methods

来源：评论

学校读者我要写书评

暂无评论

Rainfall Prediction using Novel Approach for Enhancing Crop Yield

Rainfall Prediction using Novel Approach for Enhancing Crop ...

引用

Advanced Computing & Communication Technologies (ICACCTech), International Conference on

作者： Visweswararao Seelam Sriharsha Vikruthi Naresh Kumar Bhagavatham P V V S D Nagendrudu Goda SrinivasaRao Ayyappa Chakravarthi M. Dept of CSE PACE Institute of Technology and Sciences. Dept of CSE B V Raju Institute of Technology Telangana Narsapur Medak India Dept of CSE Vignana bharathi Institute of Technology Hyderabad India Department of Artificial Intelligence and Machine Learning Aditya University Surampalem Dept of CSE KL University Vaddeswaram Guntur Andhra Pradesh Dept of CSE-Data Science KKR & KSR Institute of Technology & Sciences Guntur Andhra Pradesh

ISBN: (数字)9798331519056

ISBN: (纸本)9798331519063

In India, agriculture is one of the fastest-growing fields to improve the country's economy. Based on several factors like climatic conditions, predicting rainfall in these stages is one of the most significant tasks. In recent years, unexpected and unpredictable weather conditions have been observed in some places. This study mainly focused on developing the Hybrid algorithm (HA) to predict rainfall in the early stages and find accurate weather conditions. The proposed approach also called as Novel Approach that improves the algorithm's strength by adopting the advanced preprocessing and feature extraction technique. The training model random forest (RF) also used to find the accurate patterns from the given dataset samples. The preprocessing technique focused on cleaning and transforming the raw data to remove the noise from the input dataset, improving the data quality. The proposed approach combines Autoencoders and Linear Regression (LR) to accurately predict rainfall. Extensive experiments are carried out to evaluate the performance of the hybrid algorithm using historical meteorological data from multiple regions with varying climatic conditions. The results show that the hybrid algorithm outperforms traditional methods and individual machine-learning models in terms of accuracy, robustness, and generalization.

关键词： Radio frequency Training Rain Accuracy Temperature Autoencoders Linear regression Time series analysis Prediction algorithms data models

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：