检索结果-内蒙古大学图书馆

Towards Unified Token Learning for Vision-Language Tracking

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zheng, Yaozong Zhong, Bineng Liang, Qihua Li, Guorong Ji, Rongrong Li, Xianxian The Key Laboratory of Education Blockchain and Intelligent Technology Ministry of Education Guangxi Normal University Guilin541004 China The Guangxi Key Laboratory of Multi-Source Information Mining and Security Guangxi Normal University Guilin541004 China The School of Computer Science and Technology Key Laboratory of Big Data Mining and Knowledge Management University of Chinese Academy of Sciences Beijing100049 China Media Analytics and Computing Lab Department of Artificial Intelligence School of Informatics Xiamen University 361005 China

In this paper, we present a simple, flexible and effective vision-language (VL) tracking pipeline, termed MMTrack, which casts VL tracking as a token generation task. Traditional paradigms address VL tracking task indirectly with sophisticated prior designs, making them over-specialize on the features of specific architectures or mechanisms. In contrast, our proposed framework serializes language description and bounding box into a sequence of discrete tokens. In this new design paradigm, all token queries are required to perceive the desired target and directly predict spatial coordinates of the target in an auto-regressive manner. The design without other prior modules avoids multiple sub-tasks learning and hand-designed loss functions, significantly reducing the complexity of VL tracking modeling and allowing our tracker to use a simple cross-entropy loss as unified optimization objective for VL tracking task. Extensive experiments on TNL2K, LaSOT, LaSOText and OTB99-Lang benchmarks show that our approach achieves promising results, compared to other state-of-the-arts. Copyright © 2023, The Authors. All rights reserved.

关键词： Modeling languages

Deep diffusion-based forecasting of COVID-19 by incorporating network-level mobility information

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Roy, Padmaksha Sarkar, Shailik Biswas, Subhodip Chen, Fanglan Chen, Zhiqian Ramakrishnan, Naren Lu, Chang-Tien Department of Electrical and Computer Engineering Virginia Tech Greater Washington DC area United States Department of Computer Science Virginia Tech Greater Washington DC area United States Department of Computer Science and Engineering Mississippi State University StarkvilleMS United States Sanghani Center for Artificial Intelligence and Data Analytics Virginia Tech Greater Washington DC area United States

Modeling the spatiotemporal nature of the spread of infectious diseases can provide useful intuition in understanding the time-varying aspect of the disease spread and the underlying complex spatial dependency observed in people’s mobility patterns. Besides, the county level multiple related time series information can be leveraged to make a forecast on an individual time series. Adding to this challenge is the fact that real-time data often deviates from the unimodal Gaussian distribution assumption and may show some complex mixed patterns. Motivated by this, we develop a deep learning-based time-series model for probabilistic forecasting called Auto-regressive Mixed Density Dynamic Diffusion Network (ARM3Dnet), which considers both people’s mobility and disease spread as a diffusion process on a dynamic directed graph. The Gaussian Mixture Model layer is implemented to consider the multimodal nature of the real-time data while learning from multiple related time series. We show that our model, when trained with the best combination of dynamic covariate features and mixture components, can outperform both traditional statistical and deep learning models in forecasting the number of Covid-19 deaths and cases at the county level in the United States. Copyright © 2021, The Authors. All rights reserved.

关键词： Time series

Clinical data warehouses for disease diagnosis: A focus on exosomal MicroRNA biomarkers

学校读者我要写书评

暂无评论

Informatics in Medicine Unlocked 2023年 43卷

作者： Maolmhuaidh, Fionn Ó. Thantilage, Ranul D. Burtenshaw, Denise Raja, Khuram Le-Khac, Nhien-An Cahill, Paul Forster, Robert Kechadi, M-Tahar School of Chemical Science Dublin City University DCU Glasnevin Campus Dublin 0009 Ireland School of Computer Science University College Dublin Belfield Dublin 0004 Ireland Insight Centre for Data Analytics University College Dublin Belfield Dublin 0004 Ireland Department of Diabetes and Cardiovascular Science Centre for Health Science University of the Highlands and Islands Ness Walk Inverness IV3 5SQ United Kingdom School of Biotechnology Dublin City University DCU Glasnevin Campus Dublin 0009 Ireland

Cardiovascular disease (CVD) is a leading cause of mortality worldwide, with an intricate interplay of genetic and environmental factors contributing to disease pathogenesis. MicroRNAs (μRNAs) and long non-coding RNAs (lncRNAs), critical regulators of gene expression, have been implicated in various aspects of CVD. This review provides an overview of the roles of specific μRNAs and lncRNAs in cardiovascular health and disease, discussing their potential as biomarkers and therapeutic targets. We also delve into the various techniques, challenges, and future directions for μRNA detection and analysis, highlighting the importance of high-throughput technologies such as microarray experiments and next-generation sequencing. Moreover, the advent of Big data has necessitated efficient clinical data warehousing, a critical component of μRNA research. We further address the essential data security and privacy considerations when storing and processing sensitive μRNA data. Collectively, this review underscores the significance of μRNAs and lncRNAs in CVD and emphasizes the importance of technological advancements and responsible data management in propelling this research field forward. © 2023 The Authors

关键词： Biomarkers Cardiovascular disease Clinical data warehousing data privacy data security Long non-coding RNAs Microarray analysis Next-generation sequencing Therapeutic targets μRNA μRNA detection

LARGE LANGUAGE MODELS AS MASTER KEY: UNLOCKING THE SECRETS OF MATERIALS science WITH GPT

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Xie, Tong Wan, Yuwei Huang, Wei Zhou, Yufei Liu, Yixuan Linghu, Qingyuan Wang, Shaozhou Kit, Chunyu Grazian, Clara Zhang, Wenjie Hoex, Bram School of Photovoltaic and Renewable Energy Engineering University of New South Wales KensingtonNSW Australia GreenDynamics Pty. Ltd KensingtonNSW Australia Department of Linguistics and Translation City University of Hong Kong Hong Kong School of Mathematics and Statistics University of Sydney CamperdownNSW Australia DARE ARC Training Centre in Data Analytics for Resources and Environments Australia School of Computer Science and Engineering University of New South Wales KensingtonNSW Australia

The amount of data has growing significance in exploring cutting-edge materials and a number of datasets have been generated either by hand or automated approaches. However, the materials science field struggles to effectively utilize the abundance of data, especially in applied disciplines where materials are evaluated based on device performance rather than their properties. This article presents a new natural language processing (NLP) task called structured information inference (SII) to address the complexities of information extraction at the device level in material science. We accomplished this task by tuning GPT-3 on an existing perovskite solar cell FAIR (Findable, Accessible, Interoperable, Reusable) dataset with 91.8% F1-score and extended the dataset with data published since its release. The produced data is formatted and normalized, enabling its direct utilization as input in subsequent data analysis. This feature empowers material scientists to develop models by selecting high-quality review articles within their domain. Additionally, we designed experiments to predict the electrical performance of solar cells and design materials or devices with targeted parameters using large language models (LLMs). Our results demonstrate comparable performance to traditional machine learning methods without feature selection, highlighting the potential of LLMs to acquire scientific knowledge and design new materials akin to materials scientists. © 2023, CC BY-NC-SA.

关键词： Perovskite

Evaluating Neural Machine Comprehension Model Robustness to Noisy Inputs and Adversarial Attacks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Wu, Winston Arendt, Dustin Volkova, Svitlana Center for Language and Speech Processing Department of Computer Science Johns Hopkins University Visual Analytics Group Data Sciences and Analytics Group Pacific Northwest National Laboratory

We evaluate machine comprehension models’ robustness to noise and adversarial attacks by performing novel perturbations at the character, word, and sentence level. We experiment with different amounts of perturbations to examine model confidence and misclassification rate, and contrast model performance in adversarial training with different embedding types on two benchmark datasets. We demonstrate improving model performance with ensembling. Finally, we analyze factors that effect model behavior under adversarial training and develop a model to predict model errors during adversarial attacks. Copyright © 2020, The Authors. All rights reserved.

关键词： Benchmarking

Large Language Models as Master Key: Unlocking the Secrets of Materials science

学校读者我要写书评

暂无评论

SSRN

SSRN 2023年

作者： Xie, Tong Wan, Yuwei Zhou, Yufei Huang, Wei Liu, Yixuan Linghu, Qingyuan Wang, Shaozhou Kit, Chunyu Grazian, Clara Zhang, Wenjie Hoex, Bram School of Photovoltaic and Renewable Energy Engineering University of New South Wales KensingtonNSW Australia GreenDynamics Pty. Ltd KensingtonNSW Australia Department of Linguistics and Translation City University of Hong Kong Hong Kong School of Mathematics and Statistics University of Sydney CamperdownNSW Australia DARE ARC Training Centre in Data Analytics for Resources and Environments Australia School of Computer Science and Engineering University of New South Wales KensingtonNSW Australia

The amount of data has growing significance in exploring cutting-edge materials and a number of datasets have been generated either by hand or automated approaches. However, the materials science field struggles to effectively utilize the abundance of data, especially in applied disciplines where materials are evaluated based on device performance rather than their properties. This article presents a new natural language processing (NLP) task called structured information inference (SII) to address the complexities of information extraction at the device level in material science. We accomplished this task by fine-tuning LLaMA on an existing perovskite solar cell dataset with an 87.14% F1- score. The produced data extends the existing dataset with papers published since its release, enabling its direct utilization as input in subsequent data analysis. This feature empowers material scientists to develop models by selecting high-quality review articles within their domain. Additionally, we designed regression and classification tasks to predict the electrical performance of solar cells and design materials or devices with targeted parameters. Our results demonstrate comparable performance to traditional machine learning methods without feature selection, highlighting the potential of large language models to acquire scientific knowledge and design new materials akin to materials scientists. © 2023, The Authors. All rights reserved.

关键词： Perovskite solar cells

Detectability of hierarchical communities in networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Peel, Leto Schaub, Michael T. Department of Data Analytics and Digitalisation School of Business and Economics Maastricht University Netherlands Department of Computer Science RWTH Aachen University Germany

We study the problem of recovering a planted hierarchy of partitions in a network. The detectability of a single planted partition has previously been analysed in detail and a phase transition has been identified below which the partition cannot be detected. Here we show that, in the hierarchical setting, there exist additional phases in which the presence of multiple consistent partitions can either help or hinder detection. Accordingly, the detectability limit for non-hierarchical partitions typically provides insufficient information about the detectability of the complete hierarchical structure, as we highlight with several constructive examples. Copyright © 2020, The Authors. All rights reserved.

关键词：

DIFFERENTIAL REPLICATION IN MACHINE LEARNING

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Unceta, Irene Ni, Jordi Pujol, Oriol BBVA Data & Analytics Department of Mathematics and Computer Science Universitat de Barcelona Spain Department of Operations Innovation and Data Sciences Universitat Ramon Llull ESADE Spain Department of Mathematics and Computer Science Universitat de Barcelona Spain

When deployed in the wild, machine learning models are usually confronted with data and requirements that constantly vary, either because of changes in the generating distribution or because external constraints change the environment where the model operates. To survive in such an ecosystem, machine learning models need to adapt to new conditions by evolving over time. The idea of model adaptability has been studied from different perspectives. In this paper, we propose a solution based on reusing the knowledge acquired by the already deployed machine learning models and leveraging it to train future generations. This is the idea behind differential replication of machine learning *** Codes ***, *** Copyright © 2020, The Authors. All rights reserved.

关键词： Knowledge management

Hierarchical community structure in networks

学校读者我要写书评

暂无评论

arXiv 2020年

作者： Schaub, Michael T. Li, Jiaze Peel, Leto Department of Computer Science Rwth Aachen University Germany Department of Data Analytics and Digitalisation School of Business and Economics Maastricht University Netherlands

Modular and hierarchical community structures are pervasive in real-world complex systems. A great deal of effort has gone into trying to detect and study these structures. Important theoretical advances in the detection of modular have included identifying fundamental limits of detectability by formally defining community structure using probabilistic generative models. Detecting hierarchical community structure introduces additional challenges alongside those inherited from community detection. Here we present a theoretical study on hierarchical community structure in networks, which has thus far not received the same rigorous attention. We address the following questions: 1) How should we define a hierarchy of communities? 2) How do we determine if there is sufficient evidence of a hierarchical structure in a network? and 3) How can we detect hierarchical structure efficiently? We approach these questions by introducing a definition of hierarchy based on the concept of stochastic externally equitable partitions and their relation to probabilistic models, such as the popular stochastic block model. We enumerate the challenges involved in detecting hierarchies and, by studying the spectral properties of hierarchical structure, present an efficient and principled method for detecting them. Copyright © 2020, The Authors. All rights reserved.

关键词： Stochastic systems