检索结果-内蒙古大学图书馆

12th International Conference on Learning Representations, ICLR 2024

作者： Nie, Shen Guo, Hanzhong Allan Lu, Cheng Zhou, Yuhao Zheng, Chenyu Li, Chongxuan Gaoling School of Artificial Intelligence Renmin University of China Beijing China Beijing Key Laboratory of Big Data Management and Analysis Methods Beijing China Department of Computer Science and Technology Tsinghua University Beijing China

We present a unified probabilistic formulation for diffusion-based image editing, where a latent variable is edited in a task-specific manner and generally deviates from the corresponding marginal distribution induced by the original stochastic or ordinary differential equation (SDE or ODE). Instead, it defines a corresponding SDE or ODE for editing. In the formulation, we prove that the Kullback-Leibler divergence between the marginal distributions of the two SDEs gradually decreases while that for the ODEs remains as the time approaches zero, which shows the promise of SDE in image editing. Inspired by it, we provide the SDE counterparts for widely used ODE baselines in various tasks including inpainting and image-to-image translation, where SDE shows a consistent and substantial improvement. Moreover, we propose SDE-Drag - a simple yet effective method built upon the SDE formulation for point-based content dragging. We build a challenging benchmark (termed DragBench) with open-set natural, art, and AI-generated images for evaluation. A user study on DragBench indicates that SDE-Drag significantly outperforms our ODE baseline, existing diffusion-based methods, and the renowned DragGAN. Our results demonstrate the superiority and versatility of SDE in image editing and push the boundary of diffusion-based editing methods. See the project page https://***/SDE-Drag-demo/for the code and DragBench dataset. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Clustering Single-Cell RNA-seq data: Impact of data Binarization on Algorithmic Performance

Clustering Single-Cell RNA-seq Data: Impact of Data Binariza...

引用

18th International Joint Conference on Biomedical Engineering Systems and Technologies, BIOSTEC 2025

作者： Widzisz, Karolina Kania, Mateusz Zyla, Joanna Polański, Andrzej Department of Computer Graphics Vision and Digital Systems Silesian University of Technology Akademicka 16 Gliwice Poland Department of Applied Informatics Silesian University of Technology Akademicka 16 Gliwice Poland Department of Data Science and Engineering Silesian University of Technology Akademicka 16 Gliwice Poland

The primary objective of this study was to test the hypothesis that the binary information on the presence or absence of gene expression can sufficiently capture the inherent heterogeneity within single-cell RNA se quencing (scRNA-seq) data. This hypothesis posits that even without detailed expression levels, valuable insights about cellular diversity can be obtained. Utilizing this method can be particularly advantageous when analyzing large datasets, a common scenario in the field of scRNA-seq. In this paper, we evaluate clustering performance and cluster separability of a variety of model-based algorithms and distance-based methods to an alyze both expression level data and threshold-encoded binarized data. We examined the performance of the Bernoulli-mixture model and Gaussian-mixture model. These were compared against traditional clustering techniques such as hierarchical clustering, K-means, and the Louvain algorithm on a range of scRNA-seq datasets. Our findings reveal that mixture models exhibit a lower dependence on the specific dataset compared to distance-based methods. Mixture models, particularly, demonstrate greater efficacy in accurately estimat ing the number of clusters present within the data. Among analyzed algorithms, the Bernoulli-mixture model stands out, outperforming distance-based approaches in several key aspects. Binary data, presence/absence of gene expression, seem to be indeed adequate to capture the heterogeneity of scRNA-seq data when clus tering with methods specifically designed for binary datasets. The implications of this finding are significant, as it opens up new possibilities for simplifying data analysis in scRNA-seq studies without compromising the accuracy of the results. © 2025 by SCITEPRESS– science and Technology Publications, Lda.

关键词： data accuracy

来源：评论

学校读者我要写书评

暂无评论

dsld: A Socially Relevant Tool for Teaching statistics

arXiv

引用

arXiv 2024年

作者： Abdullah, Taha Ashok, Arjun Estrada, Brandon Matloff, Norman Mittal, Aditya Department of Computer Science University of California Davis United States Department of Statistics University of California Davis United States

The growing power of data science can play a crucial role in addressing social discrimination, necessitating nuanced understanding and effective mitigation strategies of potential biases. "data science Looks At Discrimination" (dsld) is an R and Python package designed to provide users with a comprehensive toolkit of statistical and graphical methods for assessing possible discrimination related to protected groups, such as race, gender, and age. Our software offers techniques for discrimination analysis by identifying and mitigating confounding variables, along with methods for reducing bias in predictive models. In educational settings, dsld offers instructors powerful tools to teach important statistical principles through motivating real-world examples of discrimination analysis. The inclusion of an 80-page Quarto book further supports users-from statistics educators to legal professionals-in effectively applying these analytical tools to real-world scenarios. Copyright © 2024, The Authors. All rights reserved.

关键词： data science

来源：评论

学校读者我要写书评

暂无评论

BiSHop: bi-directional cellular learning for tabular data with generalized sparse modern hopfield model 24

BiSHop: bi-directional cellular learning for tabular data wi...

引用

Proceedings of the 41st International Conference on Machine Learning

作者： Chenwei Xu Yu-Chao Huang Jerry Yao-Chieh Hu Weijian Li Ammar Gilani Hsi-Sheng Goan Han Liu Department of Computer Science Northwestern University Evanston IL Department of Physics and Center for Theoretical Physics National Taiwan University Taipei Taiwan Department of Physics and Center for Theoretical Physics and Center for Quantum Science and Engineering National Taiwan University Taipei Taiwan and Physics Division National Center for Theoretical Sciences Taipei Taiwan Department of Computer Science and Department of Statistics and Data Science Northwestern University Evanston IL

We introduce the Bi-Directional Sparse Hopfield Network (BiSHop), a novel end-to-end framework for tabular learning. BiSHop handles the two major challenges of deep tabular learning: non-rotationally invariant data structure and feature sparsity in tabular data. Our key motivation comes from the recently established connection between associative memory and attention mechanisms. Consequently, BiSHop uses a dual-component approach, sequentially processing data both column-wise and row-wise through two interconnected directional learning modules. Computationally, these modules house layers of generalized sparse modern Hopfield layers, a sparse extension of the modern Hopfield model with learnable sparsity. Methodologically, BiSHop facilitates multi-scale representation learning, capturing both intra-feature and inter-feature interactions, with adaptive sparsity at each scale. Empirically, through experiments on diverse real-world datasets, BiSHop surpasses current SOTA methods with significantly fewer HPO runs, marking it a robust solution for deep tabular learning. The code is available on GitHub; future updates are on arXiv.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Advancements in Defense Surveillance: Integrating Deep Learning and Enhanced Materials in CubeSAT Systems

Advancements in Defense Surveillance: Integrating Deep Learn...

引用

Space, Aerospace and Defence Conference (SPACE), IEEE

作者： Abhay Bhandarkar Riddhi Rai Sushma B Department of Computer Science Engineering Ramaiah Institute of Technology Bengaluru India Department of Artificial Intelligence and Data Science Ramaiah Institute of Technology Bengaluru India

ISBN: (数字)9798350367386

ISBN: (纸本)9798350367393

The current paper proposes the design and development of a novel CubeSAT system equipped with a high-resolution multispectral camera and an onboard computer (OBC) employing deep learning algorithms for real-time anomaly detection that effectively track enemy movements. The CubeSAT is intended for defense and space applications, and has shown 87% accuracy and 0.89 ROC value training on YOLOv5 for object detection. Utilizing PEEK (poly-ether-ether-ketone) material, the CubeSAT achieves significant cost and weight reductions while maintaining high strength and temperature resistance. The proposed solution leverages a constellation of polar orbiting satellites to provide comprehensive, real-time monitoring and enhanced defense capabilities.

关键词： Space vehicles Deep learning YOLO Resistance Accuracy Surveillance Software algorithms

来源：评论

学校读者我要写书评

暂无评论

Expected regret and pseudo-regret are equivalent when the optimal arm is unique

The Journal of Machine Learning Research

引用

The Journal of Machine Learning Research 2022年第1期23卷 13278-13289页

作者： Daron Anderson Douglas J. Leith Department of Computer Science and Statistics Trinity College Dublin Ireland

In online linear optimisation with stochastic losses it is common to bound the pseudo-regret of an algorithm rather than the expected regret. This is attributed to the expected fluctuations for i.i.d sums making expected regret bounds better than Ω(√T) impossible. In this paper we show that when there is a unique optimal action and the action set is a polytope the difference between pseudo-regret and expected regret is o(1). This means that the existing upper bounds on pseudoregret in the literature can immediately be extended to also upper bound the expected regret. Our results are independent of the algorithm used to select the actions and apply equally to the bandit and full-information settings.

关键词： online optimisation bandits regret

来源：评论

学校读者我要写书评

暂无评论

New Exact Solutions for the Nonlinear Coupled Time-Fractional Boussinesq-Burger Equation Using G'/G-Expansion Method 23

New Exact Solutions for the Nonlinear Coupled Time-Fractiona...

引用

23rd IEEE/ACIS International Conference on computer and Information science, ICIS 2023

作者： Guo, Caixia Li, Huapeng Feng, Wenying Chen, Fu School of Mathematics and Statistics Shanxi Datong University Shanxi Datong037009 China Trent University Department of Mathematics and Computer Science PeterboroughONK9LOG2 Canada

ISBN: (纸本)9798350345841

In this paper, we deal with the nonlinear coupled time fractional BoussinesqCBurger equation. By using (G'/G)- expansion method, the more new exact solutions of the nonlinear coupled time fractional Boussinesq-Burger equation are obtained in three cases. For the first two cases, we show the 3D -graphs, contour graphs and 2D -graphs through Matlab software to illustrate the effectiveness of the wave solutions. © 2023 IEEE.

关键词： Nonlinear equations

来源：评论

学校读者我要写书评

暂无评论

Graph Neural Networks for Optimizing Reliability in Vehicle-to-Infrastructure Communication in Autonomous Systems

Graph Neural Networks for Optimizing Reliability in Vehicle-...

引用

International Conference on Communication and Electronics Systems (ICCES)

作者： G Neelamegam J. Revathy M. Kannukkiniyal M. Devendran J. Akshya Mani Deepak Choudhry Department of Computer Science and Engineering VSB College of Engineering and Technology Coimbatore Department of Artificial Intelligence and Data Science Christ the King Engineering College Coimbatore Department of Computer Science and Engineering Kongu Engineering College Erode Department of Computer Science and Engineering Hindustan institute of technology Coimbatore Department of Computational Intelligence SRM Institute of Science and Technology Chennai Department of Computing Technologies SRM Institute of Science and Technology Chennai

ISBN: (数字)9798350377972

ISBN: (纸本)9798350377989

High reliance on autonomous systems necessitates efficient and reliable data exchange through Vehicle-to-Infrastructure (V2I) communication to have appropriate and stable network performance in dynamic vehicular environments. With heuristic approaches, Dijkstra's algorithm, and Deep Q-Networks (DQN), several methods are proposed for optimizing latency reduction, packet delivery rate improvement, and power efficiency in the direction of V2I communications. However, these approaches suffer from important challenges: low adaptability of the network to real-time dynamics, suboptimal resource usage, and difficulties in scalability towards complex large-scale networks. In this scenario, we propose a framework that incorporates a GNN inside autonomous systems for V2I communication to optimize performance. The GNN will process real-time graph features, including signal strength, packet loss, and mobility speed, as it dynamically changes in adaptation to the evolution of network behaviour and other functions. This work shows the superiority of the proposed GNN model for the efficiency of experimentally conducted simulations compared to the current models; it achieved latency reduced by up to 28%, 5-10% PDR, and 20% energy efficiency across the various scenarios with urban, rural, highway, and suburban networks. The results validate robustness and scalability for practical implementations by the proposed approach in real-world autonomous systems. Further development is possible with this framework: for example, the use of multi-agent reinforcement learning techniques within cooperative decision-making and the enhancement through blockchain-based security mechanisms to ensure the integrity of the data.

关键词： Road transportation Adaptation models Vehicle-to-infrastructure Scalability Heuristic algorithms Reinforcement learning Graph neural networks Real-time systems Energy efficiency Vehicle dynamics

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review on Deep Learning Based Fall Detection in Elderly People

A Comprehensive Review on Deep Learning Based Fall Detection...

引用

Machine Learning and Autonomous Systems (ICMLAS), International Conference on

作者： S. Venkata Suryanarayana Lakshmi H.N Posimsetti T Chiranjeevi Swamy D. Bhanu Mahesh Department of Computer Science and Engineering (Data Science) CVR College of Engineering Hyderabad India Department of Computer Science and Engineering (AI&ML) CVR College of Engineering Hyderabad India Department of Artificial Intelligence and Machine Learning Swarnandhra College of Engineering and Technology Narsapuram Andhra Pradesh India Department of Computer Science and Engineering KMIT Hyderabad India

ISBN: (数字)9798331505745

ISBN: (纸本)9798331505752

Elderly people are more vulnerable to falls, which can result in serious injuries, a lower quality of life, and higher medical expenses. Traditional fall detection methods, such as wearable sensors or vision-based systems, face limitations in accuracy, comfort, and practicality. Recent advancements in deep learning have significantly improved fall detection capabilities by leveraging powerful computational models for data analysis and feature extraction. With an emphasis on important methodologies, architectures, and datasets utilized in the area, this paper offers a thorough literature analysis of deep learning-based fall detection strategies. It investigates several deep learning techniques applied to sensor-based and video-based fall detection systems, such as convolutional neural networks (CNNs), recurrent neural networks (RNNs), and hybrid models. The review also emphasizes the difficulties encountered in practical application, including data privacy and computing cost, and the need for robust datasets. Finally, future research directions are proposed to address current limitations and improve fall detection systems' dependability and effectiveness for elderly care.

关键词： Deep learning Recurrent neural networks Reviews Computational modeling Convolutional neural networks Fall detection Older adults Wearable sensors Long short term memory Injuries

来源：评论

学校读者我要写书评

暂无评论

LSTM new gate for computing the efficiency on inputdata

引用

Knowledge-Based Systems 2025年 322卷

作者： García Cabello, Julia Carbó-García, Santiago Department of Applied Mathematics Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Department of Computer Science and Artificial Intelligence Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain

The recognized learning ability of neural networks (NNs) is determined by their training process. The NN data-dependent nature makes that their success depends to a large extent on the quality of the training data sets. This paper addresses the selection of the best training sets for Long Short Time Models (LSTMs) in real-life contexts. If such selection from a theoretical standpoint is already complex, it becomes challenging when addressed for real scenarios, where effectiveness should be replaced by efficiency (i.e., effectiveness in the shortest possible time and without increasing the computational cost). Our proposal revolves around the introduction, definition and structuring of a new LSTM gate: the efficiency gate, that applies to those inputs that have passed the forget gate. The efficiency gate is responsible for ensuring that training advances only with the best inputs in the sense that the corresponding outputs match as closely as possible with a target value (best estimators). For this purpose, new mathematical results will be demonstrated here in order to prove that our efficiency gate is mathematically feasible. We also fully describe how the new gate joins the LSTM operation, blending in with it. The consequence of such natural integration is that the computational effort is practically unchanged. Our methodology also allows the user to set the admissible error thresholds (which are different in each real scenario) as part of the setting options. © 2025 The Authors

关键词： Efficiency gate New LSTM gate Selection of training data sets Real-life contexts

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：