检索结果-内蒙古大学图书馆

Once upon a Time, in a Computer engineering Department ….

SIGMOD Record 2024年第4期52卷 36-38页

作者： Catarci, Tiziana Department of Computer Control and Management Engineering Sapienza University of Roma Italy

When you decide to pursue a career in the academy, you may encounter many difficulties, obstacles, and moments of discouragement, but also have great satisfaction, exaltation, and a lot of fun. By the time you get to the mid-career period, many doubts and problems are behind you (if you are still in the academy and did not give up) and a less stressful time begins with even more freedom to study, create your own group, and choose your own ventures. This is also the time when you may decide to impact the society, not just work for yourself, but do it to contribute to the creation of a better world and be a positive example for the younger generation. © 2024 Association for Computing Machinery. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Incremental Reinforcement Learning via Performance Evaluation and Policy Perturbation

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第5期5卷 2253-2263页

作者： Deng, Guizhou Fu, Huiqiao Wang, Xinpeng Liu, Canghai Tang, Kaiqiang Chen, Chunlin Southwest University of Science and Technology Mechanical Engineering School of Manufacturing Science and Engineering Mianyang621000 China Nanjing University School of Management and Engineering Nanjing210093 China Nanjing University Department of Control and Systems Engineering School of Management and Engineering Nanjing210093 China

Rapid adaptation to the environment is the long-term task of reinforcement learning. However, reinforcement learning faces great challenges in dynamic environments, especially with continuous state-action spaces. In this article, we propose a systematic incremental reinforcement learning method via performance evaluation and policy perturbation (IRL-PEPP) to improve the adaptability of reinforcement learning algorithms in dynamic environments with continuous state-action spaces, which mainly includes three parts, i.e., performance evaluation, policy perturbation, and importance weighting. First, in performance evaluation, we apply the learned optimal policy to sample a few episodes in the original environment and use these samples to evaluate the policy applicability in the new environment. Then, in policy perturbation, the policy is perturbed according to the policy applicability to balance the tradeoff between exploration and exploitation in the new environment. Finally, importance weighting is applied to weight the information to speed up the adjustment process of the policy. Experimental results demonstrate the feasibility and efficiency of the proposed IRL-PEPP method for continuous control tasks in comparison with the existing state-of-the-art methods. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Parallel Seeds:From Foundation Models to Foundation Intelligence for Agricultural Sustainability

引用

IEEE/CAA Journal of Automatica Sinica 2025年第3期12卷 481-484页

作者： Laiyi Fu Shunkang Ling Danyang Wu Mengzhen Kang Fei-Yue Wang Hequan Sun the Shool of Automation Science and Engineering Faculty of Electronic and Information Engineering Xi'an Jiaotong University the College of Information Engineering Northwest A&F University IEEE the State Key Laboratory of Management and Control for Complex Systems Chinese Academy of Sciences

THE development of agriculture faces significant challenges due to population growth, climate change, land depletion, and environmental pollution, threatening global food security [1]. This necessitates the development of sustainable agriculture, where a fundamental step is crop breeding to improve agronomic or economic traits, e.g., increasing yields of crops while decreasing resource usage and minimizing pollution to the environment [2].

关键词：

来源：评论

学校读者我要写书评

暂无评论

EASI: Evolutionary Adversarial Simulator Identification for Sim-to-Real Transfer 38

EASI: Evolutionary Adversarial Simulator Identification for ...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Dong, Haoyu Fu, Huiqiao Xu, Wentao Zhou, Zhehao Chen, Chunlin Department of Control Science and Intelligent Engineering School of Management and Engineering Nanjing University China

Reinforcement Learning (RL) controllers have demonstrated remarkable performance in complex robot control tasks. However, the presence of reality gap often leads to poor performance when deploying policies trained in simulation directly onto real robots. Previous sim-to-real algorithms like Domain Randomization (DR) requires domain-specific expertise and suffers from issues such as reduced control performance and high training costs. In this work, we introduce Evolutionary Adversarial Simulator Identification (EASI), a novel approach that combines Generative Adversarial Network (GAN) and Evolutionary Strategy (ES) to address sim-to-real challenges. Specifically, we consider the problem of sim-to-real as a search problem, where ES acts as a generator in adversarial competition with a neural network discriminator, aiming to find physical parameter distributions that make the state transitions between simulation and reality as similar as possible. The discriminator serves as the fitness function, guiding the evolution of the physical parameter distributions. EASI features simplicity, low cost, and high fidelity, enabling the construction of a more realistic simulator with minimal requirements for real-world data, thus aiding in transferring simulated-trained policies to the real world. We demonstrate the performance of EASI in both sim-to-sim and sim-to-real tasks, showing superior performance compared to existing sim-to-real algorithms. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Prototype-Based Interpretable Graph Neural Networks

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年第4期5卷 1486-1495页

作者： Ragno, Alessio Rosa, Biagio La Capobianco, Roberto Sapienza University of Rome Department of Computer Control and Management Engineering Rome00185 Italy Sony AI Zurich8952 Switzerland

Graph neural networks have proved to be a key tool for dealing with many problems and domains, such as chemistry, natural language processing, and social networks. While the structure of the layers is simple, it is difficult to identify the patterns learned by the graph neural network. Several works propose post hoc methods to explain graph predictions, but few of them try to generate interpretable models. Conversely, the topic of the interpretable models is highly investigated in image recognition. Given the similarity between image and graph domains, we analyze the adaptability of prototype-based neural networks for graph and node classification. In particular, we investigate the use of two interpretable networks, ProtoPNet and TesNet, in the graph domain. We show that the adapted networks manage to reach better or higher accuracy scores than their respective black-box models and comparable performances with state-of-the-art self-explainable models. Showing how to extract ProtoPNet and TesNet explanations on graph neural networks, we further study how to obtain global and local explanations for the trained models. We then evaluate the explanations of the interpretable models by comparing them with post hoc approaches and self-explainable models. Our findings show that the application of TesNet and ProtoPNet to the graph domain produces qualitative predictions while improving their reliability and transparency. © 2020 IEEE.

关键词： Computer architecture

来源：评论

学校读者我要写书评

暂无评论

A Real-Time Machine Learning Based Solution for Privacy Enforcement in Video Recordings and Live Streaming 9

A Real-Time Machine Learning Based Solution for Privacy Enfo...

引用

9th International Conference of Yearly Reports on Informatics, Mathematics, and engineering, ICYRIME 2024

作者： Conforti, Pietro Manganelli Emanuele, Matteo Mandelli, Lorenzo Department of Computer Control and Management Engineering Sapienza University of Rome Italy

These past years the world had to deal with a whole new situation brought by Covid-19. Everyone’s routine changed and we started passing way more time than before on virtual meeting, virtual chats and similar. With this, many privacy problems arised from all the video data generated by a single user. Google and Zoom introduced the possibility to blur out the background while using a front face camera, but this did not solve many privacy concerns ranging from showing people in videos without their permission, to the leaking of sensible data and information from videos uploaded online. We propose a solution build over the use of computer vision techniques like image segmentation and classification for context recognition for a privacy enforcement solution capable of fitting the user’s personal need, blurring out selectively specific objects from a video based on the user’s preferences for each room in which they are. © 2024 Copyright for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

DanteLLM: Let's Push Italian LLM Research Forward! 30

DanteLLM: Let's Push Italian LLM Research Forward!

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Bacciu, Andrea Campagnano, Cesare Trappolini, Giovanni Silvestri, Fabrizio Department of Computer Control and Management Engineering Sapienza University of Rome Italy

ISBN: (纸本)9782493814104

In recent years, the dominance of Large Language Models (LLMs) in the English language has become evident. However, there remains a pronounced gap in resources and evaluation tools tailored for non-English languages, underscoring a significant disparity in the global AI landscape. This paper seeks to bridge this gap, specifically focusing on the Italian linguistic context. We introduce a novel benchmark, and an open LLM Leaderboard, designed to evaluate LLMs' performance in Italian, providing a rigorous framework for comparative analysis. In our assessment of currently available models, we highlight their respective strengths and limitations against this standard. Crucially, we propose "DanteLLM", a state-of-the-art LLM dedicated to Italian. Our empirical evaluations underscore Dante's superiority, as it emerges as the most performant model on our benchmark, with improvements by up to 6 points. This research not only marks a significant stride in Italian-centric natural language processing but also offers a blueprint for the development and evaluation of LLMs in other languages, championing a more inclusive AI paradigm. Our code at: https://***/RSTLess-research/DanteLLM. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Conversational AI for Framed Autonomy in AI-augmented Business Process management 22

Conversational AI for Framed Autonomy in AI-augmented Busine...

引用

Best Dissertation Award, Doctoral Consortium, and Demonstration and Resources Forum at 22nd International Conference on Business Process management, BPM-D 2024

作者： Casciani, Angelo Department of Computer Control and Management Engineering Sapienza University of Rome Italy

AI-augmented Business Process management Systems (ABPMSs) represent an emerging category of process-aware information systems driven by AI technology. These systems autonomously manage the execution flow of business processes (BPs) within predefined frames, encompassing procedural and declarative specifications, which may sometimes conflict. Despite operating autonomously within these boundaries, ABPMSs require dynamic conversations with human agents. These conversations not only respond to user queries but also initiate discussions to inform them of BP progression and provide recommendations for performance improvement. This research proposal aims to leverage Conversational AI to support the ABPMS’s framed autonomy, functioning as a Decision Support System (DSS). This involves explaining system’s choices and suggesting actions when constraints are violated. This technique enables intelligent, context-aware interactions with ABPMSs, fostering user trust. Our findings indicate that Conversational AI has the potential to significantly enhance the interpretability and usability of ABPMSs, thereby facilitating improved decision-making and process optimization. © 2024 Copyright for this paper by its authors.

关键词： Chatbots

来源：评论

学校读者我要写书评

暂无评论

A Mean-Field Game for a Forward-Backward Stochastic System With Partial Observation and Common Noise

引用

IEEE/CAA Journal of Automatica Sinica 2024年第3期11卷 746-759页

作者： Pengyan Huang Guangchen Wang Shujun Wang Hua Xiao the School of Control Science and Engineering Shandong University the School of Statistics and Mathematics Shandong University of Finance and Economics IEEE the School of Management Shandong University the School of Mathematics and Statistics Shandong University

This paper considers a linear-quadratic(LQ) meanfield game governed by a forward-backward stochastic system with partial observation and common noise,where a coupling structure enters state equations,cost functionals and observation ***,to reduce the complexity of solving the meanfield game,a limiting control problem is *** virtue of the decomposition approach,an admissible control set is *** a filter technique and dimensional-expansion technique,a decentralized control strategy and a consistency condition system are derived,and the related solvability is also ***,we discuss an approximate Nash equilibrium property of the decentralized control ***,we work out a financial problem with some numerical simulations.

关键词： Decentralized control strategy ϵ-Nash equilibrium forward-backward stochastic system mean-field game partial observation

来源：评论

学校读者我要写书评

暂无评论

Dynamic Capacitated Vehicle Routing Problem with Stochastic Requests Using Deep Reinforcement Learning

Dynamic Capacitated Vehicle Routing Problem with Stochastic ...

引用

2024 IEEE International Conference on Systems, Man, and Cybernetics, SMC 2024

作者： Tang, Kaiqiang Fu, Huiqiao Liu, Jiasheng Deng, Guizhou Lu, Yuanyang Chen, Chunlin School of Management and Engineering Nanjing University Department of Control Science and Intelligent Engineering Nanjing210093 China

ISBN: (纸本)9781665410205

With the rapid growth of industries like e-commerce, food delivery, and ride-hailing, research on the Vehicle Routing Problem (VRP) is becoming increasingly relevant. However, most of the research in the field of VRP is based on static delivery tasks. In such tasks, the information about customer and order requests is provided before the delivery vehicle departs from the depot, and it remains constant during delivery. However, in the real world, the delivery tasks are often dynamic, where only some orders are known before the vehicle departs from the depot, and the rest of the orders are disclosed over time [1]. © 2024 IEEE.

关键词： Stochastic systems

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：