检索结果-内蒙古大学图书馆

Reset & Distill: A Recipe for Overcoming Negative Transfer in Continual Reinforcement Learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Ahn, Hongjoon Hyeon, Jinu Oh, Youngmin Hwang, Bosun Moon, Taesup Department of Electrical and Computer Engineering Seoul National University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Samsung Advanced Institute of Technology Korea Republic of ASRI INMC IPAI/AIIS Seoul National University Korea Republic of

We argue that one of the main obstacles for developing effective Continual Reinforcement Learning (CRL) algorithms is the negative transfer issue occurring when the new task to learn arrives. Through comprehensive experimental validation, we demonstrate that such issue frequently exists in CRL and cannot be effectively addressed by several recent work on mitigating plasticity loss of RL agents. To that end, we develop Reset & Distill (R&D), a simple yet highly effective method, to overcome the negative transfer problem in CRL. R&D combines a strategy of resetting the agent’s online actor and critic networks to learn a new task and an offline learning step for distilling the knowledge from the online actor and previous expert’s action probabilities. We carried out extensive experiments on long sequence of Meta-World tasks and show that our method consistently outperforms recent baselines, achieving significantly higher success rates across a range of tasks. Our findings highlight the importance of considering negative transfer in CRL and emphasize the need for robust strategies like R&D to mitigate its detrimental effects. © 2024, CC BY.

关键词： Reinforcement learning

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Zeng, Xianlong Gao, Yijing Liu, Ang Song, Fanghao Electrical Engineering and Computer Science Ohio University AthensOH45701 United States Data Science Institute Brown University ProvidenceRI02912 United States Global Urban Studies Program Rutgers University New BrunswickNJ08901 United States

This study introduces a simple yet effective method for identifying similar data points across non-free text domains, such as tabular and image data, using Large Language Models (LLMs). Our two-step approach involves data point summarization and hidden state extraction. Initially, data is condensed via summarization using an LLM, reducing complexity and highlighting essential information in sentences. Subsequently, the summarization sentences are fed through another LLM to extract hidden states, serving as compact, feature-rich representations. This approach leverages the advanced comprehension and generative capabilities of LLMs, offering a scalable and efficient strategy for similarity identification across diverse datasets. We demonstrate the effectiveness of our method in identifying similar data points on multiple datasets. Additionally, our approach enables non-technical domain experts, such as fraud investigators or marketing operators, to quickly identify similar data points tailored to specific scenarios, demonstrating its utility in practical applications. In general, our results open new avenues for leveraging LLMs in data analysis across various domains. © 2024, CC BY.

关键词： Adversarial machine learning

Optimizing Marker Design to Improve Precision of Optical Camera-Based Rigid-Body Motion Tracking and Correction in Medical Imaging

学校读者我要写书评

暂无评论

Optimizing Marker Design to Improve Precision of Optical Cam...

2021 IEEE Nuclear Science Symposium and Medical Imaging Conference, NSS/MIC 2021

作者： Fisher, Jonathan Kim, Chris C. Groll, Andrew Levin, Craig S. Stanford University Department of Electrical Engineering CA United States Stanford University Department of Computer Science CA United States Stanford University Department of Radiology Molecular Imaging Program CA United States Bioengineering at Stanford University Department of Radiology and by Courtesy Physics Electrical Engineering CA United States

ISBN: (纸本)9781665421133

In this work we evaluated the performance of a camera-based rigid body motion correction solution using a 2D checkerboard marker and a 3D encoded marker. The context of the results presented is in PET/MR imaging, but in principle this motion compensation method could be used in any type of medical imaging modality. A high precision, computer-controlled motion stage with four degrees of freedom was used to control the marker positions and orientations (a.k.a. 'poses'). Still images of the markers taken in different poses mimicking a patient moving her/his head from side to side, were used to assess performance of this method. Comparing the known stage motion to the estimated motion, our results indicate that the 2D marker achieves better angular accuracy while the 3D marker's translational (linear) accuracy is superior. For all axes, the angular error was less than 0.96, 0.35 [deg], and the translational error was less than 2.24, 4.76 [mm] for the 3D and 2D markers, respectively. © 2021 IEEE.

关键词： Medical imaging

Adaptive and Fair Deployment Approach to Balance Offload Traffic in Multi-UAV Cellular Networks

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Lai, Chuan-Chi Bhola Tsai, Ang-Hsun Wang, Li-Chun The Department of Information Engineering and Computer Science Feng Chia University Taichung40724 Taiwan The Electrical Engineering and Computer Science International Graduate Program National Yang Ming Chiao Tung University Hsinchu30010 Taiwan The Department of Communications Engineering Feng Chia University Taichung40724 Taiwan The Department of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan

Unmanned aerial vehicle-aided communication (UAB-BS) is a promising solution to establish rapid wireless connectivity in sudden/temporary crowded events because of its more flexibility and mobility features than conventional ground base station (GBS). Because of these benefits, UAV-BSs can easily be deployed at high altitudes to provide more line of sight (LoS) links than GBS. Therefore, users on the ground can obtain more reliable wireless channels. In practice, the mobile nature of the ground user can create uneven user density at different times and spaces. This phenomenon leads to unbalanced user associations among UAV-BSs and may cause frequent UAV-BS overload. We propose a three-dimensional adaptive and fair deployment approach to solve this problem. The proposed approach can jointly optimize the altitude and transmission power of UAV-BS to offload the traffic from overloaded UAV-BSs. The simulation results show that the network performance improves by 37.71% in total capacity, 37.48% in total energy efficiency and 16.12% in the Jain fairness index compared to the straightforward greedy approach. Copyright © 2022, The Authors. All rights reserved.

关键词： Energy efficiency

Robust Design of Observer-Based Fault Estimation and Fault-Tolerant Control for Linear Systems

学校读者我要写书评

暂无评论

Robust Design of Observer-Based Fault Estimation and Fault-T...

electrical engineering and Automatic Control (ICEEAC), International Conference on

作者： Abdesamia Azizi Tewfik Youssef Abdelmalek Kouadri Majdi Mansouri Mohamed Faouzi Mimouni Signals and Systems Laboratory University of M'Hamed Bougara Boumerdes Algeria Electrical and Computer Engineering Program Texas A&M University at Qatar Doha Qatar Automatic Systems Electrics and Environment (LAS2E) National School of Engineers of Monastir Tunisia

ISBN: (数字)9798350349740

ISBN: (纸本)9798350349757

This paper discusses the design of observer-based fault estimation (FE) and fault-tolerant control (FTC) for a linear time-invariant (LTI) system subject to uncertainties, external disturbances, actuator faults, and sensor faults. Initially, an unknown input observer for an augmented system is designed to simultaneously estimate system states, actuator faults, and sensor faults. This augmented system was created by introducing an augmented state vector composed of system states and various faults. Subsequently, the fault-tolerant controller is designed to stabilize the system outputs. To reduce the effect of disturbances on the fault estimation, and make the controller robust, the UIO and the FTC gain matrices are obtained by minimizing a multi-objective function formed from a set of performance indices defined in the frequency domain. The effectiveness of the proposed method is demonstrated through its application to a DC motor system.

关键词： Linear systems Actuators Uncertainty Frequency-domain analysis Fault tolerant systems Estimation Observers

Evolutionary Trends of Intelligent IoT Networking for Commercial and Industrial Use Cases

学校读者我要写书评

暂无评论

中国通信（英文版） 2023年第8期20卷前插1-前插4页

作者： Shuai Han Rong Bo Nadra Guizani Sai Xu Ruoyu Su Liang Xiao Cheng Li Department of Electronics and Communication Engineering Harbin Institute of Technology Communications Research Centre Canada Engineering program and the computing Research Association School of Cybersecurity Northwestern Polytechnical UniversityXi'anChina Nanjing University of Posts and Telecommunications Department of Informatics and Communication Engineering Xiamen Univer- sityFujianChina Department of Electrical and Computer Engineering of Memorial University St.John'sCanada

The intelligent Internet of Things(IIoT)is one of the key enablers for the digital transformation of traditional industries towards Industry *** services have diversified requirements due to the nature of their commercial and industrial *** various devices in IIoT environments have their unique properties in terms of resource limita-tions,network lifetimes,and application Quali-ty-of-Service(QoS)requirements which affect the performance under such applications ***,IoT devices typically have constrained power,storage,computing,high latency,massive multiple access and communications resources which limit the performance of IIoT for commercial and industrial Use *** the other hand,devices used in IIoT were not initially designed with security in mind and they had been considered *** response to the above challenges,domestic and foreign scholars have gradually carried out research on network architecture,collaborative scheduling strategy,energy supply technology,resource man-agement,and ***,the research on IIoT is still in its infancy,and has not yet formed comprehen-sive and systematic theoretical methods and technical standards.

关键词： Special issues and sections Internet of Things Intelligent systems Commercialization Requirements engineering Industrial engineering

Bayesian Inference for Non-Synchronously Observed Diffusions

学校读者我要写书评

暂无评论

arXiv 2025年

作者： Jasra, Ajay Kamatani, Kengo Wu, Amin School of Data Science The Chinese University of Hong Kong Shenzhen Shenzhen China Institute of Statistical Mathematics Tokyo190-0014 Japan Statistics Program Computer Electrical and Mathematical Sciences and Engineering Division King Abdullah University of Science and Technology Thuwal23955-6900 Saudi Arabia

We consider the problem of Bayesian inference for bi-variate data observed in time but with observation times which occur non-synchronously. In particular, this occurs in a wide variety of applications in finance, such as high-frequency trading or crude oil futures trading. We adopt a diffusion model for the data and formulate a Bayesian model with priors on unknown parameters along with a latent representation for the the so-called missing data. We then consider computational methodology to fit the model using Markov chain Monte Carlo (MCMC). We have to resort to time-discretization methods as the complete data likelihood is intractable and this can cause considerable issues for MCMC when the data are observed in low frequencies. In a high frequency observation frequencies we present a simple particle MCMC method based on an Euler–Maruyama time discretization, which can be enhanced using multilevel Monte Carlo (MLMC). In the low frequency observation regime we introduce a novel bridging representation of the posterior in continuous time to deal with the issues of MCMC in this case. This representation is discretized and fitted using MCMC and MLMC. We apply our methodology to real and simulated data to establish the efficacy of our methodology. © 2025, CC BY.

关键词： Crude oil

Cylindrical-Lens-Embedded Photonic Crystal Based on Self-Collimation 5

学校读者我要写书评

暂无评论

Cylindrical-Lens-Embedded Photonic Crystal Based on Self-Col...

5th IEEE Research and Applications of Photonics in Defense Conference, RAPID 2022

作者： Xia, Chun Gutierrez, Jesus J. Kuebler, Stephen M. Rumpf, Raymond C. Touma, Jimmy University of Central Florida The College of Optics and Photonics Creol OrlandoFL32816 United States University of Texas at El Paso Em Lab Department of Electrical and Computer Engineering El PasoTX79968 United States Materials Science and Engineering University of Central Florida Creol The College of Optics and Photonics Chemistry Department OrlandoFL32816 United States Computational Science Program University of Texas at El Paso Em Lab Department of Electrical and Computer Engineering El PasoTX79968 United States Eglin Afb AFRL/Munitions Directorate Integrated Sensing and Processing Branch FL32542 United States

Independent optical power and phase control is experimentally demonstrated in a self-collimating PC based on rod-into-wall unit cell and fabricated in a low-refractive-index medium by multiphoton lithography. © 2... 详细信息

ISBN: (数字)9781665402231

ISBN: (纸本)9781665402231

关键词： Refractive index

Unsupervised Anomaly Appraisal of Cleft Faces Using a StyleGAN2-based Model Adaptation Technique

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Hayajneh, Abdullah Shaqfeh, Mohammad Serpedin, Erchin Stotland, Mitchell A. Electrical and Computer Engineering Department Texas A&M University College StationTX United States Electrical and Computer Engineering Program Texas A&M University Doha Qatar Division of Plastic Craniofacial and Hand Surgery Sidra Medicine Weill Cornell Medical College Doha Qatar

This paper presents a novel machine learning framework to consistently detect, localize and rate congenital cleft lip anomalies in human faces. The goal is to provide a universal, objective measure of facial differences and reconstructive surgical outcomes that matches human judgments. The proposed method employs the StyleGAN2 generative adversarial network with model adaptation to produce normalized transformations of cleft-affected faces in order to allow for subsequent measurement of deformity using a pixel-wise subtraction approach (as illustrated in Figure 1). The complete pipeline of the proposed framework consists of the following steps: image preprocessing, face normalization, color transformation, morphological erosion, heat-map generation and abnormality scoring. Heatmaps that finely discern anatomic anomalies are proposed by exploiting the features of the considered framework. The proposed framework is validated through computer simulations and surveys containing human ratings. The anomaly scores yielded by the proposed computer model correlate closely with the human ratings of facial differences, leading to 0.942 Pearson’s r score. © 2022, CC BY-NC-SA.

关键词： Generative adversarial networks