检索结果-内蒙古大学图书馆

The geometry of efficient codes: How rate-distortion trade-offs distort the latent representations of generative models

引用

PLoS Computational Biology 2025年第5 May期21卷 e1012952页

作者： D'Amato, Leo Lancia, Gian Luca Pezzulo, Giovanni Department of Control and Computer Engineering Polytechnic University of Turin Turin Italy Institute of Cognitive Sciences and Technologies National Research Council Rome Italy Department of Psychology Sapienza University of Rome Rome Italy

Living organisms rely on internal models of the world to act adaptively. These models, because of resource limitations, cannot encode every detail and hence need to compress information. From a cognitive standpoint, information compression can manifest as a distortion of latent representations, resulting in the emergence of representations that may not accurately reflect the external world or its geometry. Rate-distortion theory formalizes the optimal way to compress information while minimizing such distortions, by considering factors such as capacity limitations, the frequency and the utility of stimuli. However, while this theory explains why the above factors distort latent representations, it does not specify which specific distortions they produce. To address this question, here we investigate how rate-distortion trade-offs shape the latent representations of images in generative models, specifically Beta Variational Autoencoders (β-VAEs), under varying constraints of model capacity, data distributions, and task objectives. By systematically exploring these factors, we identify three primary distortions in latent representations: prototypization, specialization, and orthogonalization. These distortions emerge as signatures of information compression, reflecting the model’s adaptation to capacity limitations, data imbalances, and task demands. Additionally, our findings demonstrate that these distortions can coexist, giving rise to a rich landscape of latent spaces, whose geometry could differ significantly across generative models subject to different constraints. Our findings contribute to explain how the normative constraints of rate-distortion theory shape the geometry of latent representations of generative models of artificial systems and living organisms. © 2025 D’Amato 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

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Manipulation of Elasto-Flexible Cables with Single or Multiple UAVs

arXiv

引用

arXiv 2025年

作者： Gabellieri, Chiara Teeuwen, Lars Shen, Yaolei Franchi, Antonio Faculty University of Twente Enschede7500 AE Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Rome00185 Italy

This work considers a large class of systems composed of multiple quadrotors manipulating deformable and extensible cables. The cable is described via a discretized representation, which decomposes it into linear springs interconnected through lumped-mass passive spherical joints. Sets of flat outputs are found for the systems. Numerical simulations support the findings by showing cable manipulation relying on flatness-based trajectories. Eventually, we present an experimental validation of the effectiveness of the proposed discretized cable model for a two-robot example. Moreover, a closed-loop controller based on the identified model and using cable-output feedback is experimentally tested. © 2025, CC BY.

关键词： Closed loop control systems

来源：评论

学校读者我要写书评

暂无评论

Coordinated Trajectories for Non-stop Flying Carriers Holding a Cable-Suspended Load

arXiv

引用

arXiv 2025年

作者： Gabellieri, Chiara Franchi, Antonio Faculty University of Twente Enschede7500 AE Netherlands Department of Computer Control and Management Engineering Sapienza University of Rome Rome00185 Italy

Multirotor UAVs have been typically considered for aerial manipulation, but their scarce endurance prevents long-lasting manipulation tasks. This work demonstrates that the non-stop flights of three or more carriers are compatible with holding a constant pose of a cable-suspended load, thus potentially enabling aerial manipulation with energy-efficient non-stop carriers. It also presents an algorithm for generating the coordinated non-stop trajectories. The proposed method builds upon two pillars: (1) the choice of n special linearly independent directions of internal forces within the 3n − 6-dimensional nullspace of the grasp matrix of the load, chosen as the edges of a Hamiltonian cycle on the graph that connects the cable attachment points on the load. Adjacent pairs of directions are used to generate n forces evolving on distinct 2D affine subspaces, despite the attachment points being generically in 3D;(2) the construction of elliptical trajectories within these subspaces by mapping, through appropriate graph coloring, each edge of the Hamiltonian cycle to a periodic coordinate while ensuring that no adjacent coordinates exhibit simultaneous zero derivatives. Combined with conditions for load statics and attachment point positions, these choices ensure that each of the n force trajectories projects onto the corresponding cable constraint sphere with non-zero tangential velocity, enabling perpetual motion of the carriers while the load is still. The theoretical findings are validated through simulations. © 2025, CC BY.

关键词： Trajectories

来源：评论

学校读者我要写书评

暂无评论

G-Anomaly: A Pyramid Graph Transformer-based Vision-Language Model for General Industrial Anomaly Detection

引用

IEEE Transactions on Automation Science and engineering 2025年

作者： Li, Jiaqi Wen, Shuhuan Fang, Bin Yanshan University Key Lab of Industrial Computer Control Engineering of Hebei Province Qinhuangdao066004 China Beiing University of Posts and Telecommunications Department of Artificial intelligence Beijing China

Visual-language alignment is crucial for enhancing the domain adaptability of industrial anomaly detection models. However, the existing methods overlook the importance of structured image representation, fail to further distinguish topological differences between anomalies and the inherent textures of products, which reduces the accuracy of semantic matching. To address this problem, we propose a novel industrial anomaly detection model G-Anomaly, to preserve the topological structure of the sample images and further enhance the model’s domain adaptability. We designed Pyramid Graph Transformer as a visual encoder to extract multi-scale visual features, which can directly preserve the structural relationships between different regions of the image, and also optimize the over-smoothing issue present in deep graph networks, thereby retaining the distinguishability of anomalous nodes. Additionally, we design a Multi-level Domain Adapter that ensures semantic consistency of anomalous features across different scales and contexts by performing visual-language matching at various resolutions and levels of abstraction. This enhances the model’s domain adaptability for anomaly detection for a wide range of industrial products. We collect and craft an actual solar panel dataset PV_actual AD, and conduct extensive experiments on the public dataset MVTec AD as well as the actual solar panel dataset PV_actual AD. This has demonstrated that G-Anomaly not only performs well in standard testing environments but also exhibits robustness and domain adaptability for anomaly detection tasks in real-world scenarios. © 2025 IEEE. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Binary Stochastic Flip Optimization for Training Binary Neural Networks

Binary Stochastic Flip Optimization for Training Binary Neur...

引用

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

作者： Tatsukichi Shibuya Nakamasa Inoue Rei Kawakami Ikuro Sato Department of Computer Science Institute of Science Tokyo Tokyo Japan Department of Systems and Control Engineering Institute of Science Tokyo Tokyo Japan Denso IT Laboratory Tokyo Japan

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

For deploying deep neural networks on edge devices with limited resources, binary neural networks (BNNs) have attracted significant attention, due to their computational and memory efficiency. However, once a neural network is binarized, finetuning it on edge devices becomes challenging because most conventional training algorithms for BNNs are designed for use on centralized servers and require storing real-valued parameters during training. To address this limitation, this paper introduces binary stochastic flip optimization (BinSFO), a novel training algorithm for BNNs. BinSFO employs a parameter update rule based on Boolean operations, eliminating the need to store real-valued parameters and thereby reducing memory requirements and computational overhead. In experiments, we demonstrated the effectiveness and memory efficiency of BinSFO in fine-tuning scenarios on six image classification datasets. BinSFO performed comparably to conventional training algorithms with a 70.7% smaller memory requirement. Code is released at https://***/TatsukichiShibuya/ICASSP2025_BinSFO

关键词： Training Speech coding Memory management Signal processing algorithms Signal processing Classification algorithms Servers Speech processing Optimization Image classification

来源：评论

学校读者我要写书评

暂无评论

Analysis and Mitigation of Soft-errors in GPU-accelerated Hyperspectral Image Classifiers

Analysis and Mitigation of Soft-errors in GPU-accelerated Hy...

引用

IEEE Design and Diagnostics of Electronic Circuits and Systems (DDECS)

作者： Sergiu-Mohamed Abed Juan-David Guerrero-Balaguera Josie E. Rodriguez Condia Gianluca De Lucia Marco Lapegna Matteo Sonza Reorda Department of Control and Computer Engineering (DAUIN) Politecnico di Torino CASD Scuola Superiore Universitaria Rome Italy Department of Mathematics and Applications University of Naples Federico II

ISBN: (数字)9798331528010

ISBN: (纸本)9798331528027

This work assesses the reliability of a hyperspectral image classifier for edge devices under transient faults by using a fine-grain strategy based on the Hardware Injection Through Program Transformation (HITPT) technique. The results identified the most vulnerable software parts and the corruption effects due to hardware faults (from 5.1% to 100.0% of accuracy drop). Then, the results supported the adoption of a selective-hardening software mechanism (based on the Duplication with Comparison strategy) to effectively mitigate the most critical effects under limited costs.

关键词： Costs Graphics processing units Reliability engineering Hardware Software Software reliability Circuit faults Transient analysis Principal component analysis Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Decoding AI Judgment: How LLMs Assess News Credibility and Bias

arXiv

引用

arXiv 2025年

作者： Loru, Edoardo Nudo, Jacopo Marco, Niccolò Di Cinelli, Matteo Quattrociocchi, Walter Department of Computer Control and Management Engineering Sapienza University of Rome Viale Ariosto 25 Rome00185 Italy Department of Computer Science Sapienza University of Rome Viale Regina Elena 295 Rome00161 Italy

Large Language Models (LLMs) are increasingly used to assess news credibility, yet little is known about how they make these judgments. While prior research has examined political bias in LLM outputs or their potential for automated fact-checking, their internal evaluation processes remain largely unexamined. Understanding how LLMs assess credibility provides insights into AI behavior and how credibility is structured and applied in large-scale language models. This study benchmarks the reliability and political classifications of state-of-the-art LLMs—Gemini 1.5 Flash (Google), GPT-4o mini (OpenAI), and LLaMA 3.1 (Meta)—against structured, expert-driven rating systems such as NewsGuard and Media Bias Fact Check. Beyond assessing classification performance, we analyze the linguistic markers that shape LLM decisions, identifying which words and concepts drive their evaluations. We uncover patterns in how LLMs associate credibility with specific linguistic features by examining keyword frequency, contextual determinants, and rank distributions. Beyond static classification, we introduce a framework in which LLMs refine their credibility assessments by retrieving external information, querying other models, and adapting their responses. This allows us to investigate whether their assessments reflect structured reasoning or rely primarily on prior learned associations. © 2025, CC BY.

关键词： Structured Query Language

来源：评论

学校读者我要写书评

暂无评论

A comparative analysis for automated information extraction from OSHA Lockout/Tagout accident narratives with Large Language Model

引用

Procedia computer Science 2025年 253卷 1362-1372页

作者： Nicolò Sabetta Francesco Costantino Sara Stabile Department of Computer Control and Management Engineering Sapienza University of Rome Via Ariosto 25 00185 Rome Italy Department of Occupational and Environmental Medicine Epidemiology and Hygiene INAIL Piazzale Giulio Pastore 6 00144 Rome Italy

Analysing workplace accidents is crucial for improving occupational safety by understanding causes and preventing recurrence. However, the primary challenge in analysing accident narratives lies in the unstructured nature of the text data. This study examines the effectiveness of Large Language Models (LLMs), specifically GPT-4 Turbo, in extracting information from lockout/tagout (LOTO) accident narratives in the Occupational Safety and Health Administration (OSHA) database. It compares the extracted features, namely the degree of fatality, nature of injury, and employee’s occupation, with those recorded by OSHA supervisors. Despite occasional misclassifications and hallucinations, GPT-4 Turbo shows significant potential in automating critical information extraction, reducing reliance on human interpretation. Moreover, the model achieved high accuracy rates for each feature. These findings suggest that LLMs can enhance occupational safety data analysis, though improvements in prompt design and verification are recommended for further accuracy.

关键词： LLM Occupational Safety Health Administration (OSHA) Industrial Safety LOTO Generative AI

来源：评论

学校读者我要写书评

暂无评论

Efficient Hybrid Multi-Population Genetic Algorithm for Multi-UAV Task Assignment in Consumer Electronics Applications

引用

IEEE Transactions on Consumer Electronics 2025年

作者： Bai, Xiaoshan Jiang, Haoyu Li, Chao Ullah, Inam Dabel, Maryam M. Al Bashir, Ali Kashif Wu, Zongze Sam, Shuzhi Shenzhen University College of Mechatronics and Control Engineering National Engineering Laboratory for Big Data System Computing Technology Shenzhen518060 China Shenzhen University College of Mechatronics and Control Engineering Shenzhen518060 China Shenzhen University Shenzhen City Joint Laboratory of Autonomous Unmanned Systems and Intelligent Manipulation Shenzhen518060 China Tashkent State University of Economics Department of Artificial Intelligence Tashkent100066 Uzbekistan University of Hafr Al Batin Department of Computer Science and Engineering College of Computer Science and Engineering Saudi Arabia Manchester Metropolitan University Manchester United Kingdom Shenzhen518060 China National University of Singapore Department of Electrical and Computer Engineering Singapore117576 Singapore

In recent years, as people’s living standards have improved and consumption concepts have been transformed, the demand for purchasing consumer electronics online has continued to grow, further stimulating the development of the logistics industry. Consequently, how to deliver consumer electronics to households at minimal cost has become a crucial factor that limits the development of the consumer technology industry. To tackle this problem, this paper studies the task assignment problem for multiple initially dispersed UAVs to deliver products to target locations while minimizing their total operation time. Each UAV can continuously provide delivery services to multiple target locations within its limited loading capacity and operation time. To solve this problem, we propose several hybrid multipopulation genetic algorithms. First, a novel crossover operator for the genetic algorithms is designed, through which a single parent chromosome can generate offspring individually. Second, two mutation mechanisms are performed to increase gene diversity. Third, multiple local search strategies are employed to enhance the populations’ fitness during each iteration of evolution. An improved 2-opt local search strategy is applied to optimize individual chromosomes when their similarity with the current best chromosome falls below a prescribed threshold. Alternatively, local search strategies are utilized for 1-opt, 2h-opt and interchange processes. Combining local search strategies, genetic operators, and the multi-population mechanism leads to several hybrid multi-population genetic algorithms. Numerical simulations and experimental tests demonstrate that the hybrid multi-population genetic algorithm, integrated with the improved 2-opt and 1-opt local search strategies, exhibits superior performance among the designed hybrid genetic algorithms, the minimum marginal cost algorithm (MMA), and the existing popular Co-evolutionary Multi-population Genetic Algorithm (CMGA). In exp

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Distributed Prescribed-Time Observer for Nonlinear Systems in Block-Triangular Form

引用

IEEE control Systems Letters 2025年 9卷 222-227页

作者： Vincent de Heij M. Umar B. Niazi Karl H. Johansson Saeed Ahmed Jan C. Willems Center for Systems and Control and the Engineering and Technology Institute Groningen Faculty of Science and Engineering University of Groningen Groningen The Netherlands Division of Decision and Control Systems Digital Futures KTH Royal Institute of Technology Stockholm Sweden Department of Electrical Engineering and Computer Science Laboratory for Information and Decision Systems Massachusetts Institute of Technology Cambridge MA USA

This letter proposes a design of a distributed prescribed-time observer for nonlinear systems representable in a block-triangular observable canonical form. Using a weighted average of neighbor estimates exchanged over a strongly connected digraph, each observer estimates the system state despite the limited observability of local sensor measurements. The proposed design guarantees that distributed state estimation errors converge to zero at a user-specified convergence time, irrespective of observers’ initial conditions. To achieve this prescribed-time convergence, distributed observers implement time-varying local output injection gains that monotonically increase and approach infinity at the prescribed time. The theoretical convergence is rigorously proven and validated through numerical simulations, where some implementation issues due to increasing gains have also been clarified.

关键词： Observers Convergence Nonlinear systems Symmetric matrices Observability Directed graphs control systems Vectors Linear systems Electronic mail

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：