检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ya-Wei Eileen Lin Yuval Kluger Ronen Talmon Viterbi Faculty of Electrical and Computer Engineering Technion Interdepartmental Program in Computational Biology and Bioinformatics Yale University Applied Math Program Yale University Department of Pathology School of Medicine Yale University

In this paper, we present Hyperbolic Diffusion Procrustes Analysis (HDPA), a new method for informative representation of hierarchical datasets based on hyperbolic geometry, diffusion geometry, and Procrustes analysis. Our method jointly embeds multiple datasets in a product manifold of hyperbolic spaces, where the data's hidden common hierarchical structure is provably recovered. In addition, our method generates an intrinsic embedding that accommodates the joint representation of multiple datasets with different features, acquired by different equipment, at different sites, or under different environmental conditions. Experimental results demonstrate the efficacy of HDPA on three biomedical datasets comprising heterogeneous gene expression and mass cytometry data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

SIMAP: A simplicial-map layer for neural networks

arXiv

引用

arXiv 2024年

作者： Gonzalez-Diaz, Rocio Gutiérrez-Naranjo, Miguel A. Paluzo-Hidalgo, Eduardo The Department of Applied Math I School of Engineering University of Sevilla Seville Spain The Department of Computer Science and Artificial Intelligence School of Engineering University of Sevilla Seville Spain The Department of Quantitative Methods Universidad Loyola Andalucía Campus Sevilla Dos Hermanas Seville Spain

In this paper, we present SIMAP, a novel layer integrated into deep learning models, aimed at enhancing the interpretability of the output. The SIMAP layer is an enhanced version of Simplicial-Map Neural Networks (SMNNs), an explainable neural network based on support sets and simplicial maps (functions used in topology to transform shapes while preserving their structural connectivity). The novelty of the methodology proposed in this paper is two-fold: Firstly, SIMAP layers work in combination with other deep learning architectures as an interpretable layer substituting classic dense final layers. Secondly, unlike SMNNs, the support set is based on a fixed maximal simplex, the barycentric subdivision being efficiently computed with a matrix-based multiplication algorithm. © 2024, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Retraction Note: An efficient quantum based D2D computation and communication approach for the internet of things

引用

Optical and Quantum Electronics 2024年第11期56卷 1-2页

作者： Mekala, M. S. Srivastava, Gautam Chun-Wei Lin, Jerry Dhiman, Gaurav Park, Ju H. Jung, Ho-Youl Department of Information and Communication Engineering Yeungnam University Gyeongsan Korea RLRC for Autonomous Vehicle Parts and Materials Innovation Yeungnam University Gyeongsan Korea Department of Math and Computer Science Brandon University Brandon Canada Western Norway University of Applied Sciences Gaurav Dhiman Bergen Norway Department of Computer Science Government Bikram College of Commerce Patiala India Department of Electrical Engineering Yeungnam University Gyeongsan Korea Research Centre for Interneural Computing China Medical University Taichung Taiwan University Centre for Research and Development Department of Computer Science and Engineering Chandigarh University Gharuan India Department of Computer Science and Engineering Graphic Era Deemed to be University Dehradun India

来源：评论

学校读者我要写书评

暂无评论

Work in Progress: Utilizing Decision Tree Analysis for engineering Students’ GPA Prediction

Work in Progress: Utilizing Decision Tree Analysis for Engin...

引用

IEEE World engineering Education Conference (EDUNINE)

作者： Prateek Shekhar Md Tarique Hasan Khan Sanjeet Gajjar School of Applied Engineering and Technology New Jersey Institute of Technology Newark NJ USA School of Math Engineering & Technology Navajo Technical University Crownpoint NM USA Department of Computer Science New Jersey Institute of Technology Newark NJ USA

Students’ grade point average (GPA) is an important indicator of students’ academic success. In our work-in-progress study, we utilized decision tree analysis to investigate patterns in predicting the GPA of engineering students, considering various demographic, socioeconomic, and academic aspects. Our analysis of the dataset consisting of engineering students’ academic records revealed several key insights. First, SAT scores emerged as a central factor in GPA prediction, with higher scores predicting better GPAs. Second, socioeconomic status also became evident among students with high SAT scores, reflecting the impact of background characteristics on academic achievements. Lastly, parent education level also stood out as significant, showing that students with highly educated parents generally achieved higher GPAs, underlining family educational background's role in success. Overall, our research adds to the existing literature by illuminating the intricate factors influencing engineering students’ GPA and provides an example of utilizing decision tree-based quantitative methods in engineering education research.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Parsoffensive: Persian Offensive Comments Dataset

Parsoffensive: Persian Offensive Comments Dataset

引用

International Conference on Web Research (ICWR)

作者： Ali Nazarizadeh Minoo Sayyadpour Omid Ebrahimkhani Amirmasoud Iravani Golnaz Ghannadan Shirazi Mojgan Behravan Department of Computer Engineering Central Tehran Branch Islamic Azad University Tehran Iran Dept. Math and Computer Science Kharazmi University Tehran Iran Department of English Translation Studies Faculty of Persian Literature and Foreign Languages Allameh Tabataba'i University Tehran Iran Department of Linguistics Faculty of Letters and Humanities Ferdowsi University of Mashhad Mashhad Iran Department of Engineering Faculty of Computer Engineering Alzahra University Tehran Iran Department of IT& Technology IU International University of Applied science Tehran Iran

ISBN: (数字)9798331508913

ISBN: (纸本)9798331508920

Offensive language detection is essential for maintaining respectful and inclusive online environments. By implementing detection systems, platforms aim to protect users from harmful content, curb the spread of hate speech, and promote positive interactions within digital communities. Leveraging natural language processing (NLP) techniques, this area has become a key focus in computational linguistics research and development. To address this challenge, we created the ParsOffensive dataset, consisting of approximately 8,433 Persian comments labeled as Offensive or Neutral. These comments were sourced from Instagram and labeled by two linguists. Machine learning models were trained on this dataset, with the ParsBert model achieving 90% accuracy in detecting offensive speech in Persian.

关键词： Accuracy Social networking (online) Computational modeling Prevention and mitigation Hate speech Text categorization Natural language processing Web sites Multimedia communication Research and development

来源：评论

学校读者我要写书评

暂无评论

Collaborative Control of Aerial Robots for Inferring Human Intent from Gaze Following

Collaborative Control of Aerial Robots for Inferring Human I...

引用

Control Technology and Applications (CCTA),

作者： Vishnu S. Chipade Alia Gilbert Daniel Harari Dimitra Panagou Department of Aerospace Engineering University of Michigan Ann Arbor MI USA Department of Robotics University of Michigan Ann Arbor MI USA Department of Computer Science and Applied Math Weizmann AI Center Weizmann Institute of Science Israel

In an ideal human-robot collaboration, autonomous robots work side-by-side with humans in a joint workspace, often performing complementary tasks to the humans. A robotic ability to infer human intention and goals directly from human behavior will facilitate the collaboration and maximize its efficiency. In this paper, we focus on inferring which object the human wants picked up next, based on what the human is looking at, by visually following the human gaze and head orientation. We develop a coordination protocol for a team of aerial robots to extract effective human head and gaze cues. The aerial robots are controlled to navigate around the human and collect data that improves the detection of the human's gaze and hence the intended object to be picked up. The effectiveness of the approach is shown using simulations in AirSim, a photo-realistic simulator.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Modeling functional cell types in spike train data

引用

PLoS Computational Biology 2023年第10 October期19卷 e1011509-e1011509页

作者： Zdeblick, Daniel N. Shea-Brown, Eric T. Witten, Daniela M. Buice, Michael A. Department of Electrical and Computer Engineering University of Washington SeattleWA United States Department of Applied Math University of Washington SeattleWA United States MindScope Program Allen Institute SeattleWA United States Department of Statistics and Biostatistics University of Washington SeattleWA United States

A major goal of computational neuroscience is to build accurate models of the activity of neurons that can be used to interpret their function in circuits. Here, we explore using functional cell types to refine single-cell models by grouping them into functionally relevant classes. Formally, we define a hierarchical generative model for cell types, single-cell parameters, and neural responses, and then derive an expectation-maximization algorithm with variational inference that maximizes the likelihood of the neural recordings. We apply this "simultaneous" method to estimate cell types and fit single-cell models from simulated data, and find that it accurately recovers the ground truth parameters. We then apply our approach to in vitro neural recordings from neurons in mouse primary visual cortex, and find that it yields improved prediction of single-cell activity. We demonstrate that the discovered cell-type clusters are well separated and generalizable, and thus amenable to interpretation. We then compare discovered cluster memberships with locational, morphological, and transcriptomic data. Our findings reveal the potential to improve models of neural responses by explicitly allowing for shared functional properties across neurons. Copyright: © 2023 Zdeblick et al. This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited.

关键词： Neurons

来源：评论

学校读者我要写书评

暂无评论

SCORE: A Second-Order Conic Initialization for Range-Aided SLAM

SCORE: A Second-Order Conic Initialization for Range-Aided S...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Alan Papalia Joseph Morales Kevin J. Doherty David M. Rosen John J. Leonard Computer Science and Artificial Intelligence Laboratory (CSAIL) Massachusetts Institute of Technology (MIT) Cambridge MA USA Department of Applied Ocean Physics & Engineering Woods Hole Oceanographic Institution Woods Hole MA USA Department of Electrical & Computer Engineering Northeastern University Boston MA USA Department of Math Northeastern University Boston MA USA

We present a novel initialization technique for the range-aided simultaneous localization and mapping (RA-SLAM) problem. In RA-SLAM we consider measurements of point-to-point distances in addition to measurements of rigid transformations to landmark or pose variables. Standard formulations of RA-SLAM approach the problem as non-convex optimization, which requires a good initialization to obtain quality results. The initialization technique proposed here relaxes the RA-SLAM problem to a convex problem which is then solved to determine an initialization for the original, non-convex problem. The relaxation is a second-order cone program (SOCP), which is derived from a quadratically constrained quadratic program (QCQP) formulation of the RA-SLAM problem. As a SOCP, the method is highly scalable. We name this relaxation Second-order COnic RElaxation for RA-SLAM (SCORE). To our knowledge, this work represents the first convex relaxation for RA-SLAM. We present real-world and simulated experiments which show SCORE initialization permits the efficient recovery of quality solutions for a variety of challenging single- and multi-robot RA-SLAM problems with thousands of poses and range measurements.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Cooperative Actor-Critic via TD Error Aggregation

arXiv

引用

arXiv 2022年

作者： Figura, Martin Lin, Yixuan Liu, Ji Gupta, Vijay Department of Electrical Engineering University of Notre Dame United States Department of Applied Math and Statistics Stony Brook University United States Department of Electrical and Computer Engineering Stony Brook University United States

In decentralized cooperative multi-agent reinforcement learning, agents can aggregate information from one another to learn policies that maximize a team-average objective function. Despite the willingness to cooperate with others, the individual agents may find direct sharing of information about their local state, reward, and value function undesirable due to privacy issues. In this work, we introduce a decentralized actor-critic algorithm with TD error aggregation that does not violate privacy issues and assumes that communication channels are subject to time delays and packet dropouts. The cost we pay for making such weak assumptions is an increased communication burden for every agent as measured by the dimension of the transmitted data. Interestingly, the communication burden is only quadratic in the graph size, which renders the algorithm applicable in large networks. We provide a convergence analysis under diminishing step size to verify that the agents maximize the team-average objective function. © 2022, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Energy grid management system with anomaly detection and Q-learning decision modules

引用

computers and Electrical engineering 2023年 107卷

作者： Syu, Jia-Hao Srivastava, Gautam Fojcik, Marcin Cupek, Rafal Lin, Jerry Chun-Wei Department of Computer Science and Information Engineering National Taiwan University Taipei Taiwan Department of Mathematics and Computer Science Brandon University Brandon Canada Research Center for Interneural Computing China Medical University Taichung Taiwan Department of Computer Science and Math Lebanese American University Beirut Lebanon Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway Department of Distributed Systems and Informatic Devices Silesian University of Technology Gliwice Poland

Stability and security issues in energy management have become widespread research topics, in which artificial intelligence techniques are often embedded in management systems to efficiently manage the smart grid. In this paper, we propose an energy grid management system with anomaly detection and Q-learning decision modules (EMSAD). The anomaly detection module is a multitask learning network that simultaneously classifies suppliers and predicts actual supply quantities. The Q-learning decision module then determines the operating reserve and subsidies to manage the energy grid. Experimental results show that the proposed anomaly detection module has an excellent performance in classifying malicious suppliers with F1-scores from 73.3% to 100.0%. The robustness evaluation also shows that EMSAD maintains high performance even in unseen environments without fine-tuning. Thus, the simulation results demonstrate the security, efficiency, transferability, and robustness of the proposed EMSAD in smart grid energy management. © 2023 Elsevier Ltd

关键词： Energy management

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：