检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Lai, Song Zhao, Zhe Zhu, Fei Lin, Xi Zhang, Qingfu Meng, Gaofeng Department of Computer Science City University of Hong Kong Hong Kong Centre for Artificial Intelligence and Robotics HK Institute of Science & Innovation Chinese Academy of Sciences China State Key Laboratory of Multimodal Artificial Intelligence Systems Institute of Automation Chinese Academy of Sciences China School of Artificial Intelligence University of Chinese Academy of Sciences China City University of Hong Kong Shenzhen Research Institute Hong Kong University of Science and Technology of China China

Continual learning aims to learn multiple tasks sequentially. A key challenge in continual learning is balancing between two objectives: retaining knowledge from old tasks (stability) and adapting to new tasks (plasticity). Experience replay methods, which store and replay past data alongside new data, have become a widely adopted approach to mitigate catastrophic forgetting. However, these methods neglect the dynamic nature of the stability-plasticity trade-off and aim to find a fixed and unchanging balance, resulting in suboptimal adaptation during training and inference. In this paper, we propose Pareto Continual Learning (ParetoCL), a novel framework that reformulates the stability-plasticity trade-off in continual learning as a multi-objective optimization (MOO) problem. ParetoCL introduces a preference-conditioned model to efficiently learn a set of Pareto optimal solutions representing different trade-offs and enables dynamic adaptation during inference. From a generalization perspective, ParetoCL can be seen as an objective augmentation approach that learns from different objective combinations of stability and plasticity. Extensive experiments across multiple datasets and settings demonstrate that ParetoCL outperforms state-of-the-art methods and adapts to diverse continual learning scenarios. Copyright © 2025, The Authors. All rights reserved.

关键词： Multi-task learning

来源：评论

学校读者我要写书评

暂无评论

Directly wireless communication of human minds via non-invasive brain-computer-metasurface platform

arXiv

引用

arXiv 2022年

作者： Ma, Qian Gao, Wei Xiao, Qiang Ding, Lingsong Gao, Tianyi Zhou, Yajun Gao, Xinxin Yan, Tao Liu, Che Gu, Ze Kong, Xianghong Abbasi, Qammer H. Li, Lianlin Qiu, Cheng-Wei Li, Yuanqing Cui, Tie Jun Institute of Electromagnetic Space Southeast University Nanjing210096 China School of Automation Science and Engineering South China University of Technology Guangzhou510641 China State Key Laboratory of Millimeter Wave Southeast University Nanjing210096 China Center of Intelligent Metamaterials Pazhou Laboratory Guangzhou510330 China Research Center for Brain-Computer Interface Pazhou Lab Guangzhou510330 China Department of Electrical and Computer Engineering National University of Singapore Singapore Singapore University of Glasgow James Watt School of Engineering GlasgowG12 8QQ United Kingdom State Key Laboratory of Advanced Optical Communication Systems and Networks Department of Electronics Peking University Beijing100871 China

Brain-computer interfaces (BCIs), invasive or non-invasive, have projected unparalleled vision and promise for assisting patients in need to better their interaction with the surroundings. Inspired by the BCI-based rehabilitation technologies for nerve-system impairments and amputation, we propose an electromagnetic brain-computer-metasurface (EBCM) paradigm, regulated by human's cognition by brain signals directly and non-invasively. We experimentally show that our EBCM platform can translate human's mind from evoked potentials of P300-based electroencephalography to digital coding information in the electromagnetic domain non-invasively, which can be further processed and transported by an information metasurface in automated and wireless fashions. Directly wireless communications of the human minds are performed between two EBCM operators with accurate text transmissions. Moreover, several other proof-of-concept mind-control schemes are presented using the same EBCM platform, exhibiting flexibly-customized capabilities of information processing and synthesis like visual-beam scanning, wave modulations, and pattern encoding. © 2022, CC BY.

关键词： Electrophysiology

来源：评论

学校读者我要写书评

暂无评论

An ecologically valid examination of event-based and time-based prospective memory using immersive virtual reality: The influence of attention, memory, and executive function processes on real-world prospective memory.

TechRxiv

引用

TechRxiv 2021年

作者： Kourtesis, Panagiotis MacPherson, Sarah E. Human Cognitive Neuroscience Department of Psychology University of Edinburgh Edinburgh United Kingdom Department of Psychology University of Edinburgh Edinburgh United Kingdom Lab of Experimental Psychology Suor Orsola Benincasa University of Naples Naples Italy Interdepartmental Centre for Planning and Research "Scienza Nuova" Suor Orsola Benincasa University of Naples Naples Italy National Research Institute of Computer Science and Automation INRIA Rennes France Univ Rennes Rennes France gResearch Institute of Computer Science and Random Systems IRISA Rennes France French National Centre for Scientific Research CNRS Rennes France Department of Psychology University of Edinburgh 7 George Square EdinburghEH8 9JZ United Kingdom

Studies on prospective memory (PM) predominantly assess either event- or time-based PM by implementing non-ecological laboratory-based tasks. The results deriving from these paradigms have provided findings that are discrepant with ecologically valid research paradigms that converge on the complexity and cognitive demands of everyday tasks. The Virtual Reality Everyday Assessment Lab (VR-EAL), an immersive virtual reality (VR) neuropsychological battery with enhanced ecological validity, was implemented to assess everyday event- and time-based PM, as well as the influence of other cognitive functions on everyday PM functioning. The results demonstrated the importance of delayed recognition, planning, and visuospatial attention on everyday PM. Delayed recognition and planning ability were found to be central in event- and time-based PM respectively. In order of importance, delayed recognition, visuospatial attention speed, and planning ability were found to be involved in event-based PM functioning. Comparably, planning, visuospatial attention accuracy, delayed recognition, and multitasking/task-shifting ability were found to be involved in time-based PM functioning. These findings further suggest the importance of ecological validity in the study of PM, which may be achieved using immersive VR paradigms. © 2021, CC BY.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

Adjacency Constraint for Efficient Hierarchical Reinforcement Learning

arXiv

引用

arXiv 2021年

作者： Zhang, Tianren Guo, Shangqi Tan, Tian Hu, Xiaolin Chen, Feng The Department of Automation Tsinghua University Beijing100086 China The Beijing Innovation Center for Future Chip Beijing100086 China The LSBDPA Beijing Key Laboratory Beijing100084 China The Department of Civil and Environmental Engineering Stanford University Stanford CA94305 United States The Department of Computer Science and Technology Institute for Artificial Intelligence Beijing National Research Center for Information Science and Technology State Key Laboratory of Intelligent Technology and Systems Tsinghua University Beijing100084 China

Goal-conditioned Hierarchical Reinforcement Learning (HRL) is a promising approach for scaling up reinforcement learning (RL) techniques. However, it often suffers from training inefficiency as the action space of the high-level, i.e., the goal space, is large. Searching in a large goal space poses difficulty for both high-level subgoal generation and low-level policy learning. In this paper, we show that this problem can be effectively alleviated by restricting the high-level action space from the whole goal space to a k-step adjacent region of the current state using an adjacency constraint. We theoretically prove that in a deterministic Markov Decision Process (MDP), the proposed adjacency constraint preserves the optimal hierarchical policy, while in a stochastic MDP the adjacency constraint induces a bounded state-value suboptimality determined by the MDP’s transition structure. We further show that this constraint can be practically implemented by training an adjacency network that can discriminate between adjacent and non-adjacent subgoals. Experimental results on discrete and continuous control tasks including challenging simulated robot locomotion and manipulation tasks show that incorporating the adjacency constraint significantly boosts the performance of state-of-the-art goal-conditioned HRL approaches. Copyright © 2021, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

When counterpoint meets chinese folk melodies 20

When counterpoint meets chinese folk melodies

引用

Proceedings of the 34th International Conference on Neural Information Processing systems

作者： Nan Jiang Sheng Jin Zhiyao Duan Changshui Zhang Institute for Artificial Intelligence Tsinghua University (THUAI) and State Key Lab of Intelligent Technologies and Systems and Beijing National Research Center for Information Science and Technology (BNRist) and Department of Automation Tsinghua University Beijing China Department of Electrical and Computer Engineering University of Rochester

ISBN: (纸本)9781713829546

Counterpoint is an important concept in Western music theory. In the past century, there have been significant interests in incorporating counterpoint into Chinese folk music composition. In this paper, we propose a reinforcement learning-based system, named FolkDuet, towards the online countermelody generation for Chinese folk melodies. With no existing data of Chinese folk duets, FolkDuet employs two reward models based on out-of-domain data i.e., Bach chorales, and monophonic Chinese folk melodies. An interaction reward model is trained on the duets formed from outer parts of Bach chorales to model counterpoint interaction, while a style reward model is trained on monophonic melodies of Chinese folk songs to model melodic patterns. With both rewards, the generator of FolkDuet is trained to generate countermelodies while maintaining the Chinese folk style. The entire generation process is performed in an online fashion, allowing real-time interactive human-machine duet improvisation. Experiments show that the proposed algorithm achieves better subjective and objective results than the baselines.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Regret and Cumulative Constraint Violation Analysis for distributed Online Constrained Convex Optimization

arXiv

引用

arXiv 2021年

作者： Yi, Xinlei Li, Xiuxian Yang, Tao Xie, Lihua Chai, Tianyou Johansson, Karl H. The Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden The Digital Futures Stockholm10044 Sweden The Department of Control Science and Engineering College of Electronics and Information Engineering The Shanghai Research Institute for Intelligent Autonomous Systems Tongji University Shanghai China The State Key Laboratory of Synthetical Automation for Process Industries Northeastern University Shenyang110819 China School of Electrical and Electronic Engineering Nanyang Technological University 50 Nanyang Avenue Singapore639798 Singapore

This paper considers the distributed online convex optimization problem with time-varying constraints over a network of agents. This is a sequential decision making problem with two sequences of arbitrarily varying convex loss and constraint functions. At each round, each agent selects a decision from the decision set, and then only a portion of the loss function and a coordinate block of the constraint function at this round are privately revealed to this agent. The goal of the network is to minimize the network-wide loss accumulated over time. Two distributed online algorithms with full-information and bandit feedback are proposed. Both dynamic and static network regret bounds are analyzed for the proposed algorithms, and network cumulative constraint violation is used to measure constraint violation, which excludes the situation that strictly feasible constraints can compensate the effects of violated constraints. In particular, we show that the proposed algorithms achieve O(T max{κ,1-κ}) static network regret and O(T 1-κ/2) network cumulative constraint violation, where T is the time horizon and κ ∈ (0, 1) is a user-defined trade-off parameter. Moreover, if the loss functions are strongly convex, then the static network regret bound can be reduced to O(T κ). Finally, numerical simulations are provided to illustrate the effectiveness of the theoretical results. Copyright © 2021, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Risk-sensitive safety analysis using Conditional Value-at-Risk

arXiv

引用

arXiv 2021年

作者： Chapman, Margaret P. Bonalli, Riccardo Smith, Kevin M. Yang, Insoon Pavone, Marco Tomlin, Claire J. The Edward S. Rogers Sr. Department of Electrical and Computer Engineering University of Toronto TorontoONM5S 3G4 Canada CentraleSupélec France The Department of Civil and Environmental Engineering Tufts University MedfordMA02155 United States OptiRTC Inc. BostonMA02116 United States The Department of Electrical and Computer Engineering Automation and Systems Research Institute Seoul National University Seoul Korea Republic of The Department of Aeronautics and Astronautics Stanford University StanfordCA94305 United States The Department of Electrical Engineering and Computer Sciences University of California Berkeley BerkeleyCA94720 United States

This paper develops a safety analysis method for stochastic systems that is sensitive to the possibility and severity of rare harmful outcomes. We define risk-sensitive safe sets as sub-level sets of the solution to a non-standard optimal control problem, where a random maximum cost is assessed via Conditional Value-at-Risk (CVaR). The objective function represents the maximum extent of constraint violation of the state trajectory, averaged over a given percentage of worst cases. This problem is well-motivated but difficult to solve tractably because the temporal decomposition for CVaR is history-dependent. Our primary theoretical contribution is to derive computationally tractable under-approximations to risk-sensitive safe sets. Our method provides a novel, theoretically guaranteed, parameter-dependent upper bound to the CVaR of a maximum cost without the need to augment the state space. For a fixed parameter value, the solution to only one Markov decision process problem is required to obtain the under-approximations for any family of risk-sensitivity levels. In addition, we propose a second definition for risk-sensitive safe sets and provide a tractable method for their estimation without using a parameter-dependent upper bound. The second definition is expressed in terms of a new coherent risk functional, which is inspired by CVaR. We demonstrate our primary theoretical contribution via numerical examples. Copyright © 2021, The Authors. All rights reserved.

关键词： Stochastic systems

来源：评论

学校读者我要写书评

暂无评论

Bayesian Neural Networks Uncertainty Quantification with Cubature Rules

Bayesian Neural Networks Uncertainty Quantification with Cub...

引用

International Joint Conference on Neural Networks (IJCNN)

作者： Peng Wang Nidhal C. Bouaynaya Lyudmila Mihaylova Jikai Wang Qibin Zhang Renke He Automatic Control & Systems Engineering Dept. The University of Sheffield Information and Navigation College Air Force Engineering University The 32nd Research Institute of CETC Department of Automation University of Science and Technology of China Department of Electrical and Computer Engineering Rowan University

ISBN: (数字)9781728169262

ISBN: (纸本)9781728169279

Bayesian neural networks are powerful inference methods by accounting for randomness in the data and the network model. Uncertainty quantification at the output of neural networks is critical, especially for applications such as autonomous driving and hazardous weather forecasting. However, approaches for theoretical analysis of Bayesian neural networks remain limited. This paper makes a step forward towards mathematical quantification of uncertainty in neural network models and proposes a cubature-rule-based computationally-efficient uncertainty quantification approach that captures layer-wise uncertainties of Bayesian neural networks. The proposed approach approximates the first two moments of the posterior distribution of the parameters by propagating cubature points across the network nonlinearities. Simulation results show that the proposed approach can achieve more diverse layer-wise uncertainty quantification results of neural networks with a fast convergence rate.

关键词： Neural networks Uncertainty Bayes methods Computational modeling Gaussian distribution Two dimensional displays Weather forecasting

来源：评论

学校读者我要写书评

暂无评论

Possibilities of vehicle state estimation using big data approaches 16

Possibilities of vehicle state estimation using big data app...

引用

16th Mini Conference on Vehicle System Dynamics, Identification and Anomalies, VSDIA 2018

作者： Fényes, Dániel Németh, Balázs Gáspár, Péter Asszonyi, Máté Systems and Control Laboratory Computer and Automation Research Institute Kende u. 13-17 Budapest Hungary Department of Control for Transportation and Vehicle Systems Faculty of Transportation Engineering and Vehicle Engineering Budapest University of Technology and Economics Stoczek u. 2 BudapestH-1111 Hungary

Nowadays, the development of the autonomous vehicles is one of the most important challenges for the automotive industry. In general, these vehicles are equipped with numerous sensors, such as onboard-camera, lidar, radar, ultrasonic sensor, accelerometer and gyroscope. These sensors provide information about the environment and other vehicles. This information is not only processed and used directly on the car but also can be stored on internal or cloud-based memory. This collected data might contain hidden information about the motion and the dynamical behaviour of the car. This hidden information can be brought out of the datasets by using big data-based data mining approaches. The aim of the paper is to create a vehicle state estimation model based on the collected sensor data and using data mining tools. In the paper, the sensor data is collected from a high-fidelity simulation software, CarSim. The estimation model is created by the machine-learning software Weka. Finally, the created model is validated through several CarSim simulations. © 2019 Budapest University of Technology and Economics. All rights reserved.

关键词： computer software

来源：评论

学校读者我要写书评

暂无评论

State estimation of an electro-pneumatic gearbox actuator

引用

IFAC-PapersOnLine 2019年第5期52卷 329-334页

作者： Adam Szabo Tamas Becsi Peter Gaspar Szilard Aradi Department of Control for Transportation and Vehicle Systems Budapest University of Technology and Economics Budapest Hungary Computer and Automation Research Institute Hungarian Academy of Sciences Budapest Hungary

This paper presents two state estimator algorithms, a Kalman and an Extended Kalman filter in order to determine the chamber pressures of a pneumatic actuator without the application of pressure sensors. The presented state estimators were validated against laboratory measurements, then it was shown, that in applications with high computational resources, such as simulations both algorithms can provide acceptable results and they have nearly the same accuracy. Meanwhile, in embedded systems with higher realizable sample time the Kalman filter, which is based on the linearized state-space representation of the system, can not handle the nonlinear behavior of the actuator in every test case. Based on the validation results, a suggestion was made in order to further improve the accuracy of the presented methods.

关键词： Pneumatic actuator State observer Kalman filter Extended Kalman filter Nonlinear system

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：