检索结果-内蒙古大学图书馆

Proceedings of the 41st International Conference on Machine Learning

作者： Daniel Levine Syed Asad Rizvi Sacha Lévy Nazreen Pallikkavaliyaveetil David Zhang Xingyu Chen Sina Ghadermarzi Ruiming Wu Zihe Zheng Ivan Vrkic Anna Zhong Daphne Raskin Insu Han Antonio Henrique De Oliveira Fonseca Josue Ortega Caro Amin Karbasi Rahul M. Dhodapkar David Van Dijk Department of Computer Science Yale University New Haven CT School of Engineering Applied Science University of Pennsylvania Philadelphia PA School of Computer and Communication Sciences Swiss Federal Institute of Technology Lausanne Lausanne Switzerland Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Department of Neuroscience Yale School of Medicine New Haven CT and Wu Tsai Institute Yale University New Haven CT Google and Yale Institute for Foundations of Data Science New Haven CT and Department of Computer Science Yale University New Haven CT and Yale School of Engineering and Applied Science New Haven CT Roski Eye Institute University of Southern California Los Angeles CA and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT Department of Computer Science Yale University New Haven CT and Yale Institute for Foundations of Data Science New Haven CT and Wu Tsai Institute Yale University New Haven CT and Cardiovascular Research Center Yale School of Medicine New Haven CT and Interdepartmental Program in Computational Biology & Bioinformatics Yale University New Haven CT and Department of Internal Medicine (Cardiology) Yale School of Medicine New Haven CT

We introduce Cell2Sentence (C2S), a novel method to directly adapt large language models to a biological context, specifically single-cell transcriptomics. By transforming gene expression data into "cell sentences," C2S bridges the gap between natural language processing and biology. We demonstrate cell sentences enable the fine-tuning of language models for diverse tasks in biology, including cell generation, complex cell-type annotation, and direct data-driven text generation. Our experiments reveal that GPT-2, when fine-tuned with C2S, can generate biologically valid cells based on cell type inputs, and accurately predict cell types from cell sentences. This illustrates that language models, through C2S fine-tuning, can acquire a significant understanding of single-cell biology while maintaining robust text generation capabilities. C2S offers a flexible, accessible framework to integrate natural language processing with transcriptomics, utilizing existing models and libraries for a wide range of biological applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Audio Segmentation Techniques and applications Based on Deep Learning

引用

Scientific Programming 2022年第0期2022卷

作者： Aggarwal, Shruti Vasukidevi, G. Selvakanmani, S. Pant, Bhaskar Kaur, Kiranjeet Verma, Amit Binegde, Geleta Negasa Department of Computer Science and Engineering Thapar University Punjab Patiala147004 India Department of Science and Humanities R.M.K. College of Engineering and Technology R.S.M. Nagar Tamil Nadu Puduvoyal India Department of Artificial Intelligence and Data Science Velammal Institute of Technology Velammal Knowledge Park Tamil Nadu Chennai India Department of Computer Science and Engineering Graphic Era Deemed to be University Bell Road Clement Town Uttarakhand Dehradun248002 India University Center for Research and Development Chandigarh University Punjab Ajitgarh India Department of Computer Science College of Engineering and Technology Mettu University Metu Ethiopia

Audio processing has become an inseparable part of modern applications in domains ranging from health care to speech-controlled devices. In automated audio segmentation, deep learning plays a vital role. In this article, we are discussing audio segmentation based on deep learning. Audio segmentation divides the digital audio signal into a sequence of segments or frames and then classifies these into various classes such as speech recognition, music, or noise. Segmentation plays an important role in audio signal processing. The most important aspect is to secure a large amount of high-quality data when training a deep learning network. In this study, various application areas, citation records, documents published year-wise, and source-wise analysis are computed using Scopus and Web of science (WoS) databases. The analysis presented in this paper supports and establishes the significance of the deep learning techniques in audio segmentation. Copyright © 2022 Shruti Aggarwal et al. This is an open access article distributed under the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Structured Downsampling for Fast, Memory-efficient Curation of Online data Streams

arXiv

引用

arXiv 2024年

作者： Moreno, Matthew Andres Zaman, Luis Dolson, Emily Department of Ecology and Evolutionary Biology Ann Arbor United States Center for the Study of Complex Systems Ann Arbor United States Michigan Institute for Data and AI in Society Ann Arbor United States University of Michigan Ann Arbor United States Department of Computer Science and Engineering East Lansing United States Program in Ecology Evolution and Behavior East Lansing United States Michigan State University East Lansing United States

Operations over data streams typically hinge on efficient mechanisms to aggregate or summarize history on a rolling basis. For high-volume data steams, it is critical to manage state in a manner that is fast and memory efficient - particularly in resource-constrained or real-time contexts. Here, we address the problem of extracting a fixed-capacity, rolling subsample from a data stream. Specifically, we explore "data stream curation" strategies to fulfill requirements on the composition of sample time points retained. Our "DStream" suite of algorithms targets three temporal coverage criteria: (1) steady coverage, where retained samples should spread evenly across elapsed data stream history;(2) stretched coverage, where early data items should be proportionally favored;and (3) tilted coverage, where recent data items should be proportionally favored. For each algorithm, we prove worst-case bounds on rolling coverage quality. In contrast to previous work by Moreno, Rodriguez Papa, and Dolson (2024), which dynamically scales memory use to guarantee a specified level of coverage quality, here we focus on the more practical, application-driven case of maximizing coverage quality given a fixed memory capacity. As a core simplifying assumption, we restrict algorithm design to a single update operation: writing from the data stream to a calculated buffer site - with data never being read back, no metadata stored (e.g., sample timestamps), and data eviction occurring only implicitly via overwrite. Drawing only on primitive, low-level operations and ensuring full, overhead-free use of available memory, this "DStream" framework ideally suits domains that are resource-constrained (e.g., embedded systems), performance-critical (e.g., real-time), and fine-grained (e.g., individual data items as small as single bits or bytes). In particular, proposed power-of-two-based buffer layout schemes support O(1) data ingestion via concise bit-level operations. To further practical applica

关键词： data streams

来源：评论

学校读者我要写书评

暂无评论

Ultra-Sensitive Optical Fiber Spr Biosensor for Precise Prostate Cancer Diagnosis by Label-Free Detection of Mirna-21

SSRN

引用

SSRN 2025年

作者： Wang, Jiale Deng, Minghua Niu, Kunpeng Wang, Chuanquan Wang, Ning Li, Jinhua Xia, Binyun Ding, Liyun Yang, Huan Chen, Xiaohan Zhu, Jiayi National Engineering Research Center of Fiber Optic Sensing Technology and Networks Wuhan University of Technology Wuhan430070 China School of Computer and Information Engineering Hubei Normal University Huangshi China Hubei Optical Fundamental Research Center Wuhan China Collaborative Innovation Center for Advanced Organic Chemical Materials Co-constructed by the Province and Ministry Key Laboratory for the Green Preparation and Application of Functional Materials Ministry of Education Hubei Key Laboratory of Polymer Materials School of Materials Science and Engineering Hubei University Wuhan430062 China School of Physical Science and Technology Lanzhou University Lanzhou730000 China Department of Urology Tongji Hospital Tongji Medical College Huazhong University of Science and Technology Wuhan430030 China

Efficient and rapid identification of miRNA-21 may be conducive to the early diagnosis of prostate cancer. In this work, a label-free and highly sensitive optical fiber Surface Plasmon Resonance (SPR) biosensor was developed for detecting the miRNA-21, which was fabricated simply by coating a layer of Au film and AuNPs onto a multi-mode-single-mode-multi-mode (MSM) optical fiber, and then biofunctionalized with ssDNA enabling the quantification of miRNA-21. The working principle involves initiating the change of the effective refractive index (RI) around the optical fiber's surface, which was caused by nucleic acid hybridization between the ssDNA and the miRNA-21. As a result, the interaction would result in a noticeable shift of the SPR wavelengths in the transmission spectra. In the experiment, a substantial enhancement was exhibited in the RI sensitivity of the optical fiber sensor due to the surface plasmon resonance (SPR) coupling effect of AuNPs and the Au film, measuring approximately 3021.48 nm/RIU. Excitingly, the biosensors, which have a simple composition, were experimentally verified to have an ultra-low limit of detection (LOD) of 10-20 M, significantly lower than current detection methods. And trace miRNA-21 was enabled for detection without RNA amplification. The SPR sensors were also experimentally proved with excellent linearity, specificity and stability. When employed to detect the serum samples, the results indicated that the proposed sensors could brilliantly distinguish clinical patients with and without prostate cancer. Compared to the commonly used PSA quantification in clinical practice, the method developed in this work has higher detection accuracy. The proposed sensing platform processes the merits of simple configuration as well as low cost and may be applied for the precise diagnosis of prostate cancer. © 2025, The Authors. All rights reserved.

关键词： Surface plasmon resonance

来源：评论

学校读者我要写书评

暂无评论

A Survey for Large Language Models in Biomedicine

arXiv

引用

arXiv 2024年

作者： Wang, Chong Li, Mengyao He, Junjun Wang, Zhongruo Darzi, Erfan Chen, Zan Ye, Jin Li, Tianbin Su, Yanzhou Ke, Jing Qu, Kaili Li, Shuxin Yu, Yi Liò, Pietro Wang, Tianyun Wang, Yu Guang Shen, Yiqing School of Medical Engineering Xinxiang Medical University Xinxiang China Engineering Technology Research Center of Neurosense and Control of Henan Province Xinxiang China Henan International Joint Laboratory of Neural Information Analysis and Drug Intelligent Design Xinxiang China Shanghai AI Laboratory Shanghai China Amazon Palo AltoCA United States Boston Children's Hospital MA United States Harvard Medical School Harvard University MA United States Toursun Synbio Shanghai China Department of Data Science & AI Faculty of IT Monash University Melbourne Australia School of Electronic Information and Electrical Engineering Shanghai Jiao Tong University Shanghai China School of Computer Science and Engineering University of New South Wales Sydney Australia Department of Computer Science and Technology University of Cambridge Cambridge United Kingdom School of Basic Medical Sciences Xinxiang Medical University Xinxiang China Institute of Natural Sciences Shanghai Jiao Tong University Shanghai China School of Mathematics and Statistics University of New South Wales Sydney Australia Department of Computer Science Johns Hopkins University MD United States

Recent breakthroughs in large language models (LLMs) offer unprecedented natural language understanding and generation capabilities. However, existing surveys on LLMs in biomedicine often focus on specific applications or model architectures, lacking a comprehensive analysis that integrates the latest advancements across various biomedical domains. This review, based on an analysis of 484 publications sourced from databases including PubMed, Web of science, and arXiv, provides an in-depth examination of the current landscape, applications, challenges, and prospects of LLMs in biomedicine, distinguishing itself by focusing on the practical implications of these models in real-world biomedical contexts. Firstly, we explore the capabilities of LLMs in zero-shot learning across a broad spectrum of biomedical tasks, including diagnostic assistance, drug discovery, and personalized medicine, among others, with insights drawn from 137 key studies. Then, we discuss adaptation strategies of LLMs, including fine-tuning methods for both uni-modal and multi-modal LLMs to enhance their performance in specialized biomedical contexts where zero-shot fails to achieve, such as medical question answering and efficient processing of biomedical literature. Finally, we discuss the challenges that LLMs face in the biomedicine domain including data privacy concerns, limited model interpretability, issues with dataset quality, and ethics due to the sensitive nature of biomedical data, the need for highly reliable model outputs, and the ethical implications of deploying ai in healthcare. To address these challenges, we also identify future research directions of LLM in biomedicine including federated learning methods to preserve data privacy and integrating explainable ai methodologies to enhance the transparency of LLMs. As this field of LLM rapidly evolves, continued research and development are essential to fully harness the capabilities of LLMs in biomedicine while ensuring their respon

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Phylotrack: C++ and Python libraries for in silico phylogenetic tracking

arXiv

引用

arXiv 2024年

作者： Dolson, Emily Rodruigez-Papa, Santiago Moreno, Matthew Andres Department of Computer Science and Engineering Michigan State University East LansingMI48823 United States Ecology Evolution and Behavior Michigan State University East LansingMI48823 United States Department of Ecology and Evolutionary Biology University of Michigan Ann ArborMI48103 United States Center for the Study of Complex Systems University of Michigan Ann ArborMI48103 United States Michigan Institute for Data Science and AI in Society University of Michigan Ann ArborMI48103 United States

In silico evolution instantiates the processes of heredity, variation, anddifferential reproductive success (the three "ingredients" for evolution bynatural selection) within digital populations of computational ***, these populations undergo evolution, and can be used as virtualmodel systems for studying evolutionary dynamics. This experimental paradigm -used across biological modeling, artificial life, and evolutionary computation- complements research done using in vitro and in vivo systems by enablingexperiments that would be impossible in the lab or field. One key benefit iscomplete, exact observability. For example, it is possible to perfectly recordall parent-child relationships across simulation history, yielding completephylogenies (ancestry trees). This information reveals when traits were gainedor lost, and also facilitates inference of underlying evolutionary dynamics. The Phylotrack project provides libraries for tracking and analyzingphylogenies in in silico evolution. The project is composed of 1)Phylotracklib: a header-only C++ library, developed under the umbrella of theEmpirical project, and 2) Phylotrackpy: a Python wrapper around Phylotracklib,created with Pybind11. Both components supply a public-facing API to attachphylogenetic tracking to digital evolution systems, as well as a stand-aloneinterface for measuring a variety of popular phylogenetic topology *** design and C++ implementation prioritizes efficiency, allowing forfast generational turnover for agent populations numbering in the tens ofthousands. Several explicit features (e.g., phylogeny pruning and abstraction,etc.) are provided for reducing the memory footprint of phylogeneticinformation. Copyright © 2024, The Authors. All rights reserved.

关键词： C++ (programming language)

来源：评论

学校读者我要写书评

暂无评论

Point-Snamae: Att-Masked Autoencoder Based on Self-Distillation And Normal Vector Estimation for Self-Supervised Point Cloud Representation Learning

SSRN

引用

SSRN 2024年

作者： Liu, Jie Yang, Mengna Tian, Yu Li, Yancui Song, Da Li, Kang Cao, Xin College of Computer and Information Engineering Henan Normal University Henan Xinxiang453007 China Big Data Engineering Laboratory for Teaching Resources & Assessment of Education Quality Henan Xinxiang453007 China School of Information Science and Technology Northwest University Shaanxi Xi’an China National and Local Joint Engineering Research Center for Cultural Heritage Digitization Shaanxi Xi’an710127 China Bioresource Engineering Department McGill University MontrealQC Canada

Masked signal modeling (MSM) has gained considerable attention in self-supervised learning. Considering that the existing masked strategies may cause the model to damage the structural or semantic understanding of key regions, we present an improved masked auto-encoder based on self-distillation and normal vector prediction that can augment the capacity to recognize local regions. Firstly, given a point cloud with a normal vector, our approach involves the grouping and embedding of point clouds lacking a corresponding normal vector. Secondly, based on self-distillation, the teacher branch guides the student branch to perform regional masking according to an embedded self-attention matrix. Due to the point cloud’s redundancy, the encoder utilizes a high ratio as input and greatly alleviates the input. At the same time, to prevent the model learning difficulty caused by too few inputs from affecting the robustness of model learning, our method only retains a small number of high score regions. Finally, the feature representation of the teacher-student branches is supervised by patch and global losses to comprehensively evaluate the learning performance of the mask patches. Taking normal vector estimation as a supervisory signal to improve global representation. Extensive experiments have shown that our approach is effective and well-transferable to a variety of downstream tasks. Specifically, our model achieves an accuracy of 94.12% on ModelNet40 and 87.16% on the PB-T50-RS setting of ScanObjectNN, outperforming other self-supervised learning methods. Our method achieved a remarkable accuracy of 98.4% in the 5-way 20-shot setting of Few Shot Learning. For part segmentation, our method achieves competitive results with other self-supervised methods. © 2024, The Authors. All rights reserved.

关键词： Supervised learning

来源：评论

学校读者我要写书评

暂无评论

Kernel-based off-policy estimation without overlap: Instance optimality beyond semiparametric efficiency

arXiv

引用

arXiv 2023年

作者： Mou, Wenlong Ding, Peng Wainwright, Martin J. Bartlett, Peter L. Department of Electrical Engineering and Computer Sciences United States Department of Statistics UC Berkeley United States Laboratory for Information and Decision Systems EECS and Mathematics Massachusetts Institute of Technology United States Statistics and Data Science Center EECS and Mathematics Massachusetts Institute of Technology United States Google Research United States

We study optimal procedures for estimating a linear functional based on observational data. In many problems of this kind, a widely used assumption is strict overlap, i.e., uniform boundedness of the importance ratio, which measures how well the observational data covers the directions of interest. When it is violated, the classical semi-parametric efficiency bound can easily become infinite, so that the instance-optimal risk depends on the function class used to model the regression function. For any convex and symmetric function class F, we derive a non-asymptotic local minimax bound on the mean-squared error in estimating a broad class of linear functionals. This lower bound refines the classical semi-parametric one, and makes connections to moduli of continuity in functional estimation. When F is a reproducing kernel Hilbert space, we prove that this lower bound can be achieved up to a constant factor by analyzing a computationally simple regression estimator. We apply our general results to various families of examples, thereby uncovering a spectrum of rates that interpolate between the classical theories of semi-parametric efficiency (with √n-consistency) and the slower minimax rates associated with non-parametric function estimation. Copyright © 2023, The Authors. All rights reserved.

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

Recent research on Artificial Intelligence, Machine Learning, and Deep Learning in Consumer Electronics Technology

Recent Research on Artificial Intelligence, Machine Learning...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Brij B. Gupta Akshat Gaurav Varsha Arya Kwok Tai Chui Department of Computer Science and Information Engineering International Center for AI and Cyber Security Research and Innovations (CCRI) Asia University Taichung Taiwan Lebanese American University Beirut Lebanon Ronin Institute Montclair NJ USA Asia University Taichung Taiwan Hong Kong Metropolitan University (HKMU) Hong Kong

In this article, we show how research on artificial intelligence (ai), machine learning (ML), and deep learning (DL) has been used to develop consumer electronics (CE) technology from 1985 to 2022. The most significant themes for CE are discovered by a combination of quantitative and qualitative methods. The examination of the subject was based on quantitative data groups and themes. In addition, this research employs thematic maps to illustrate the connections between the core principles of the CE community.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Near-Field Beam Focusing Pattern and Grating Lobe Characterization for Modular XL-Array

arXiv

引用

arXiv 2023年

作者： Li, Xinrui Dong, Zhenjun Zeng, Yong Jin, Shi Zhang, Rui National Mobile Communications Research Laboratory Frontiers Science Center for Mobile Information Communication and Security Southeast University Nanjing210096 China Purple Mountain Laboratories Nanjing211111 China Shenzhen Research Institute of Big Data Shenzhen518172 China Department of Electrical and Computer Engineering National University of Singapore Singapore117583 Singapore

In this paper, we investigate the near-field modelling and analyze the beam focusing pattern for modular extremely large-scale array (XL-array) communications. As modular XL-array is physically and electrically large in general, the accurate characterization of amplitude and phase variations across its array elements requires the non-uniform spherical wave (NUSW) model, which, however, is difficult for performance analysis and optimization. To address this issue, we first present two ways to simplify the NUSW model by exploiting the unique regular structure of modular XL-array, termed sub-array based uniform spherical wave (USW) models with different or common angles, respectively. Based on the developed models, the near-field beam focusing patterns of XL-array communications are derived. It is revealed that compared to the existing collocated XL-array with the same number of array elements, modular XL-array can significantly enhance the spatial resolution, but at the cost of generating undesired grating lobes. Fortunately, different from the conventional far-field uniform plane wave (UPW) model, the near-field USW model for modular XL-array exhibits a higher grating lobe suppression capability, thanks to the non-linear phase variations across the array elements. Finally, simulation results are provided to verify the near-field beam focusing pattern and grating lobe characteristics of modular XL-array. Copyright © 2023, The Authors. All rights reserved.

关键词： Focusing

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：