检索结果-内蒙古大学图书馆

IEEE Transactions on Artificial Intelligence 2021年第3期2卷 214-227页

作者： Amir Emad Marvasti Ehsan Emad Marvasti Ulas Bagci Hassan Foroosh Computational Imaging Lab University of Central Florida Orlando FL USA Department of Computer Science University of Central Florida Orlando FL USA Center for Research in Computer Vision University of Central Florida Orlando FL USA

We present a theoretical framework of probabilistic learning derived from the maximum probability (MP) theorem shown in this article. In this probabilistic framework, a model is defined as an event in the probability space, and a model or the associated event—either the true underlying model or the parameterized model—has a quantified probability measure. This quantification of a model's probability measure is derived by the MP theorem, in which we have shown that an event's probability measure has an upper bound given its conditional distribution on an arbitrary random variable. Through this alternative framework, the notion of model parameters is encompassed in the definition of the model or the associated event. Therefore, this framework deviates from the conventional approach of assuming a prior on the model parameters. Instead, the regularizing effects of assuming prior over parameters are imposed through maximizing probabilities of models or, according to information theory, minimizing the information content of a model. The probability of a model in our framework is invariant to reparameterization and is solely dependent on the model's likelihood function. In addition, rather than maximizing the posterior in a conventional Bayesian setting, the objective function in our alternative framework is defined as the probability of set operations (e.g., intersection) on the event of the true underlying model and the event of the model at hand. Our theoretical framework adds clarity to probabilistic learning through solidifying the definition of probabilistic models, quantifying their probabilities, and providing a visual understanding of objective functions. Impact Statement —The choice of prior distribution over the parameters of probabilistic machine learning models determines the regularization of learning algorithms in the Bayesian perspective. The complexity in choice of prior over the parameters and the form of regularization is relative to the complexi

关键词： Random variables Bayes methods Probabilistic logic Machine learning Linear programming Entropy Complexity theory

来源：评论

学校读者我要写书评

暂无评论

A Simulated real-world upper-body Exoskeleton Accident and Investigation

arXiv

引用

arXiv 2024年

作者： Winfield, Alan F.T. Webb, Nicola Etoundi, Appolinaire Derval, Romain Salvini, Pericle Jirotka, Marina Bristol Robotics Lab University of the West of England BristolBS16 1QY United Kingdom Tribonix Ltd. Bristol Business School Room 2x102 Frenchay Campus Coldharbour Lane Bristol BS16 1QY United Kingdom Department of Computer Science University of Oxford Oxford United Kingdom

This paper describes the enactment of a simulated (mock) accident involving an upper-body exoskeleton and its investigation. The accident scenario is enacted by role-playing volunteers, one of whom is wearing the exoskeleton. Following the mock accident, investigators - also volunteers - interview both the subject of the accident and relevant witnesses. The investigators then consider the witness testimony alongside robot data logged by the ethical black box, in order to address the three key questions: what happened?, why did it happen?, and how can we make changes to prevent the accident happening again? This simulated accident scenario is one of a series we have run as part of the RoboTIPS project, with the overall aim of developing and testing both processes and technologies to support social robot accident investigation. © 2024, CC BY.

关键词： Exoskeleton (robotics)

来源：评论

学校读者我要写书评

暂无评论

DMPCN: Dynamic Modulated Predictive Coding Network with Hybrid Feedback Representations

arXiv

引用

arXiv 2025年

作者： Sagar, A.S.M. Sharifuzzaman Chen, Yu Chan, Jun Hoong Department of Artificial Intelligence and Robotics Sejong University Seoul Korea Republic of AI Lab MetaSyntec School of Computer Science Peking University Beijing China

Traditional predictive coding networks, inspired by theories of brain function, consistently achieve promising results across various domains, extending their influence into the field of computer vision. However, the performance of the predictive coding networks is limited by their error feedback mechanism, which traditionally employs either local or global recurrent updates, leading to suboptimal performance in processing both local and broader details simultaneously. In addition, traditional predictive coding networks face difficulties in dynamically adjusting to the complexity and context of varying input data, which is crucial for achieving high levels of performance in diverse scenarios. Furthermore, there is a gap in the development and application of specific loss functions that could more effectively guide the model towards optimal performance. To deal with these issues, this paper introduces a hybrid prediction error feedback mechanism with dynamic modulation for deep predictive coding networks by effectively combining global contexts and local details while adjusting feedback based on input complexity. Additionally, we present a loss function tailored to this framework to improve accuracy by focusing on precise prediction error minimization. Experimental results demonstrate the superiority of our model over other approaches, showcasing faster convergence and higher predictive accuracy in CIFAR-10, CIFAR-100, MNIST, and FashionMNIST datasets. © 2025, CC BY.

关键词： Network coding

来源：评论

学校读者我要写书评

暂无评论

Nucleon isovector momentum fraction, helicity and transversity moment using Lattice QCD 38

Nucleon isovector momentum fraction, helicity and transversi...

引用

38th International Symposium on Lattice Field Theory, LATTICE 2021

作者： Mondal, Santanu Bhattacharya, Tanmoy Gupta, Rajan Joó, Bálint Lin, Huey-Wen Park, Sungwoo Winter, Frank Yoon, Boram Los Alamos National Laboratory Theoretical Division T-2 Los AlamosNM87545 United States Oak Ridge Leadership Computing Facility Oak Ridge National Laboratory Oak RidgeTN37831 United States Department of Physics and Astronomy Michigan State University MI48824 United States Department of Computational Mathematics Science and Engineering Michigan State University MI48824 United States Jefferson Lab 12000 Jefferson Avenue Newport NewsVA23606 United States Los Alamos National Laboratory Computer Computational and Statistical Sciences CCS-7 Los AlamosNM87545 United States

We present our recent high precision calculations [1, 2] of the first moment of nucleon isovector polarized, unpolarized and transversity distributions, i.e., momentum fraction, helicity and transversity moment, respectively. We use the standard method for the calculation of these moments (via matrix elements of twist two operators), and carry out a detailed analysis of the sources of systematic uncertainty, in particular of excited state contributions. Our calculations have been performed using two different lattice setups (Clover-on-HISQ and Clover-on-Clover), each with several ensembles. They give consistent results that are in agreement with global fit analyses. © Copyright owned by the author(s) under the terms of the Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License (CC BY-NC-ND 4.0)

关键词： Excited states

来源：评论

学校读者我要写书评

暂无评论

Full wCDM analysis of KiDS-1000 weak lensing maps using deep learning

引用

Physical Review D 2022年第8期105卷 083518-083518页

作者： Janis Fluri Tomasz Kacprzak Aurelien Lucchi Aurel Schneider Alexandre Refregier Thomas Hofmann Institute of Particle Physics and Astrophysics Department of Physics ETH Zurich Wolfang-Pauli-Strasse 27 8093 Zurich Switzerland Data Analytics Lab Department of Computer Science ETH Zurich Universitätstrasse 6 8006 Zurich Switzerland Swiss Data Science Center Paul Scherrer Institute Forschungsstrasse 111 5232 Villigen Switzerland Department of Mathematics and Computer Science University of Basel Spiegelgasse 1 4051 Basel Switherland Center for Theoretical Astrophysics and Cosmology Institute for Computational Science University of Zurich Winterthurerstrasse 190 8057 Zurich Switzerland

We present a full forward-modeled wCDM analysis of the KiDS-1000 weak lensing maps using graph-convolutional neural networks (GCNN). Utilizing the cosmogrid, a novel massive simulation suite spanning six different cosmological parameters, we generate almost one million tomographic mock surveys on the sphere. Due to the large dataset size and survey area, we perform a spherical analysis while limiting our map resolution to HEALPix nside=512. We marginalize over systematics such as photometric redshift errors, multiplicative calibration and additive shear bias. Furthermore, we use a map-level implementation of the nonlinear intrinsic alignment model along with a novel treatment of baryonic feedback to incorporate additional astrophysical nuisance parameters. We also perform a spherical power spectrum analysis for comparison. The constraints of the cosmological parameters are generated using a likelihood-free inference method called Gaussian process approximate Bayesian computation (GPABC). Finally, we check that our pipeline is robust against choices of the simulation parameters. We find constraints on the degeneracy parameter of S8≡σ8ΩM/0.3=0.78−0.06+0.06 for our power spectrum analysis and S8=0.79−0.05+0.05 for our GCNN analysis, improving the former by 16%. This is consistent with earlier analyses of the 2-point function, albeit slightly higher. Baryonic corrections generally broaden the constraints on the degeneracy parameter by about 10%. These results offer great prospects for full machine learning based analyses of ongoing and future weak lensing surveys.

关键词： Cosmological parameters Large scale structure of the Universe Particle dark matter Numerical simulations in gravitation & astrophysics

来源：评论

学校读者我要写书评

暂无评论

Dissecting Self-Supervised Learning Methods for Surgical computer Vision

arXiv

引用

arXiv 2022年

作者： Ramesh, Sanat Srivastav, Vinkle Alapatt, Deepak Yu, Tong Murali, Aditya Sestini, Luca Nwoye, Chinedu Innocent Hamoud, Idris Sharma, Saurav Fleurentin, Antoine Exarchakis, Georgios Karargyris, Alexandros Padoy, Nicolas ICube University of Strasbourg CNRS Strasbourg67000 France IHU Strasbourg Strasbourg67000 France Altair Robotics Lab Department of Computer Science University of Verona Verona37134 Italy Department of Electronics Information and Bioengineering Politecnico di Milano Milano20133 Italy

The field of surgical computer vision has undergone considerable breakthroughs in recent years with the rising popularity of deep neural network-based methods. However, standard fully-supervised approaches for training such models require vast amounts of annotated data, imposing a prohibitively high cost;especially in the clinical domain. Self-Supervised Learning (SSL) methods, which have begun to gain traction in the general computer vision community, represent a potential solution to these annotation costs, allowing to learn useful representations from only unlabeled data. Still, the effectiveness of SSL methods in more complex and impactful domains, such as medicine and surgery, remains limited and unexplored. In this work, we address this critical need by investigating four state-of-the-art SSL methods (MoCo v2, SimCLR, DINO, SwAV) in the context of surgical computer vision. We present an extensive analysis of the performance of these methods on the Cholec80 dataset for two fundamental and popular tasks in surgical context understanding, phase recognition and tool presence detection. We examine their parameterization, then their behavior with respect to training data quantities in semi-supervised settings. Correct transfer of these methods to surgery, as described and conducted in this work, leads to substantial performance gains over generic uses of SSL - up to 7.4% on phase recognition and 20% on tool presence detection - as well as state-of-the-art semi-supervised phase recognition approaches by up to 14%. Further results obtained on a highly diverse selection of surgical datasets exhibit strong generalization properties. The code is available at https://***/CAMMA-public/SelfSupSurg. © 2022, CC BY-SA.

关键词： computer vision

来源：评论

学校读者我要写书评

暂无评论

Pushing the Boundaries of computational Empowerment of Children 25

Pushing the Boundaries of Computational Empowerment of Child...

引用

Proceedings of the 24th Interaction Design and Children

作者： Netta Iivari Ole Sejer Iversen Yasmin Kafai Alissa N. Antle Marianne Graves Petersen Marianne Kinnula Christian Dindler Fares Kayali Elizabeth Bonsignore Charu Monga, Ms. Marie-Monique Schaper Sumita Sharma INTERACT Research Unit University of Oulu Oulu Finland Center for Computational Thinking and Design Aarhus University Aarhus Denmark Graduate School of Education University of Pennsylvania Philadelphia Pennsylvania USA School of Interactive Arts and Technology Simon Fraser University Vancouver British Columbia Canada Computer Science Aarhus University Aarhus Århus Denmark University of Vienna Vienna Austria Human-Computer Interaction Lab University of Maryland College Park Maryland USA Department of Design Indian Institute of Technology Delhi Delhi India Department for Computer Engineering and Digital Design University of Lleida Lleida Spain

ISBN: (纸本)9798400714733

Emerging technologies such as artificial intelligence (AI) and mixed reality (MR) increasingly pervade the world of children, from their schoolwork to leisure activities and social relationships. This has led to Child computer Interaction (CCI) research supporting children's critical understanding of digital technologies and their ability to influence the design of future digital technologies. Despite these efforts, there are several limitations and challenges in terms of computational Empowerment (CE) of children. This workshop unites such research 1) to create a shared manifesto for CE of children and 2) to jointly develop a research ‘roadmap’ to push the boundaries of CE of children.

关键词： Child computer Interaction computational Empowerment Participatory Design Critical Computing Emerging Technologies

来源：评论

学校读者我要写书评

暂无评论

Advancing Speaker Embedding Learning: Wespeaker Toolkit for Research and Production

SSRN

引用

SSRN 2024年

作者： Wang, Shuai Chen, Zhengyang Han, Bing Wang, Hongji Liang, Chengdong Zhang, Binbin Xiang, Xu Ding, Wen Rohdin, Johan Silnova, Anna Qian, Yanmin Li, Haizhou Shenzhen Institute of Big Data Guangdong Shenzhen China Department of Computer Science and Engineering Shanghai Jiao Tong University Shanghai China Tencent Ethereal Audio Lab Tencent Corporation Shenzhen China Horizon Robotics Beijing China NVIDIA Shanghai China Brno University of Technology Faculty of Information Technology IT4I Centre of Excellence Czech Republic School of Data Science The Chinese University of Hong Kong Guangdong Shenzhen China

Speaker modeling plays a crucial role in various tasks, and fixed-dimensional vector representations, known as speaker embeddings, are the predominant modeling approach. These embeddings are typically evaluated within the framework of speaker verification, yet their utility extends to a broad scope of related tasks including speaker diarization, speech synthesis, voice conversion, and target speaker extraction. This paper presents Wespeaker, a user-friendly toolkit designed for both research and production purposes, dedicated to the learning of speaker embeddings. Wespeaker offers scalable data management, state-of-the-art speaker embedding models, and self-supervised learning training schemes with the potential to leverage large-scale unlabeled real-world data. The toolkit incorporates structured recipes that have been successfully adopted in winning systems across various speaker verification challenges, ensuring highly competitive results. For production-oriented development, Wespeaker integrates CPU- and GPUcompatible deployment and runtime codes, supporting mainstream platforms such as Windows, Linux, Mac and on-device chips such as horizon X3’PI. Wespeaker also provides off-the-shelf high-quality speaker embeddings by providing various pretrained models, which can be effortlessly applied to different tasks that require speaker modeling. The toolkit is publicly available at https://***/wenet-e2e/wespeaker. © 2024, The Authors. All rights reserved.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

redPATH:Reconstructing the Pseudo Development Time of Cell Lineages in Single-cell RNA-seq Data and Applications in Cancer

引用

Genomics, Proteomics & Bioinformatics 2021年第2期19卷 292-305页

作者： Kaikun Xie Zehua Liu Ning Chen Ting Chen Institute for Artificial Intelligence State Key Lab of Intelligent Technology and SystemsDepartment of Computer Science and TechnologyTsinghua UniversityBeijing 100084China Tsinghua-Fuzhou Institute of Digital Technology Beijing National Research Center for Information Science and TechnologyTsinghua UniversityBeijing 100084China Center for Computational and Integrative Biology Massachusetts General HospitalHarvard Medical SchoolBostonMA 02114USA Department of Molecular Biology Massachusetts General HospitalHarvard Medical SchoolBostonMA 02114USA Broad Institute of Massachusetts Institute of Technology and Harvard CambridgeMA 02142USA

The recent advancement of single-cell RNA sequencing(scRNA-seq)technologies facilitates the study of cell lineages in developmental processes and *** this study,we developed a computational method,called redPATH,to reconstruct the pseudo developmental time of cell lineages using a consensus asymmetric Hamiltonian path ***,we developed a novel approach to visualize the trajectory development and implemented visualization methods to provide biological *** validated the performance of redPATH by segmenting different stages of cell development on multiple neural stem cell and cancer datasets,as well as other single-cell transcriptome *** particular,we identified a stem cell-like subpopulation in malignant glioma *** cells express known proliferative markers,such as GFAP,ATP1A2,IGFBPL1,and ALDOC,and remain silenced for quiescent markers such as ***,we identified MCL1 as a significant gene that regulates cell apoptosis and CSF1R for reprogramming macrophages to control tumor *** conclusion,redPATH is a comprehensive tool for analyzing scRNA-seq datasets along the pseudo developmental *** is available at https://***/tinglabs/redPATH.

关键词： Single-cell pseudotime reconstruction Consensus Hamiltonian path Cell differentiation Cell proliferation Cell development and diseases

来源：评论

学校读者我要写书评

暂无评论

What can real information content tell us about compressing climate model data?

What can real information content tell us about compressing ...

引用

IEEE/ACM International Workshop on Data Analysis and Reduction for Big Scientific Data (DRBSD-5)

作者： Hayden Sather Alexander Pinard Allison H. Baker Dorit M. Hammerling Department of Computer Science Colorado School of Mines Golden CO USA Applied Mathematics and Statistics Colorado School of Mines Golden CO USA Computational and Information Systems Lab National Center for Atmospheric Research Boulder CO USA

ISBN: (纸本)9781665463386

The massive data volumes produced by climate simulation models create an urgent need for data reduction. Lossy compression in particular is a solution that can significantly reduce storage requirements, however, a tradeoff must be made between the amount of compression applied and the scientific integrity of the data. Determining how much compression can be applied is therefore vital for applying lossy compression. One particular metric for gauging the quality of compression is the percentage of real information present in the original data that is preserved in the compressed data. We compute bitwise real information content for several climate variables from the popular Community Earth System Model, and we investigate the amount of compression that can be applied to each of these climate variables using two popular compression algorithms designed for floating-point data while preserving 99% of the real information content. The analysis of the real information content of data after lossy compression has been applied shows a helpful visualization of how compression artifacts have been introduced to the data. Finally, we demonstrate how this real information content can be used in a straightforward manner to determine compressor settings for our data.

关键词： Measurement Earth Analytical models Data analysis Conferences computational modeling Data visualization

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：