检索结果-南通市图书馆

维普期刊数据库

Federated Meta Reinforcement Learning for Personalized Tasks

在线全文

学校读者我要写书评

暂无评论

Tsinghua science and Technology 2024年第3期29卷 911-926页

作者： Wentao Liu Xiaolong Xu Jintao Wu Jielin Jiang school of Computer science Nanjing University of Information Science and TechnologyNanjing 210044China school of Software Nanjing University of Information Science and TechnologyNanjing 210044China

As an emerging privacy-preservation machine learning framework,Federated Learning(FL)facilitates different clients to train a shared model collaboratively through exchanging and aggregating model parameters while raw data are kept local and *** this learning framework is applied to Deep Reinforcement Learning(DRL),the resultant Federated Reinforcement Learning(FRL)can circumvent the heavy data sampling required in conventional DRL and benefit from diversified training data,besides privacy preservation offered by *** FRL implementations presuppose that clients have compatible tasks which a single global model can *** practice,however,clients usually have incompatible(different but still similar)personalized tasks,which we called task *** may severely hinder the implementation of FRL for practical *** this paper,we propose a Federated Meta Reinforcement Learning(FMRL)framework by integrating Model-Agnostic Meta-Learning(MAML)and ***,we innovatively utilize Proximal Policy Optimization(PPO)to fulfil multi-step local training with a single round of ***,considering the sensitivity of learning rate selection in FRL,we reconstruct the aggregation optimizer with the Federated version of Adam(Fed-Adam)on the server *** experiments demonstrate that,in different environments,FMRL outperforms other FL methods with high training efficiency brought by Fed-Adam.

关键词： federated learning reinforcement learning meta-learning personalization

Neural network study of the nuclear ground-state spin distribution within a random interaction ensemble

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

Nuclear science and Techniques 2024年第3期35卷 216-227页

作者： Deng Liu Alam Noor A Zhen-Zhen Qin Yang Lei school of Mathematics and Physics Southwest University of Science and TechnologyMianyang 621010China school of Nuclear science and Technology Southwest University of Science and TechnologyMianyang 621010China

The distribution of the nuclear ground-state spin in a two-body random ensemble(TBRE)was studied using a general classification neural network(NN)model with two-body interaction matrix elements as input features and the corresponding ground-state spins as labels or output *** quantum many-body system problem exceeds the capability of our optimized NNs in terms of accurately predicting the ground-state spin of each sample within the ***,our NN model effectively captured the statistical properties of the ground-state spin because it learned the empirical regularity of the ground-state spin distribution in TBRE,as discovered by physicists.

关键词： Neural network Two-body random ensemble Spin distribution of nuclear ground state

维普期刊数据库

Dual template-induced construction of three-dimensional porous SiO2/NC/Co-CNTs heterostructure with highly dispersed active sites for efficient oxygen evolution reaction

在线全文

学校读者我要写书评

暂无评论

Tungsten 2024年第3期6卷 585-595页

作者： Hai-Qi Zhang Xiao-Jun Zeng Qing-Qing Zhang Zu-Liang Zhang Chu-Long Jin Rong-Hai Yu school of Materials science and Engineering Jingdezhen Ceramic University school of Materials science and Engineering Beihang University

The development and exploration of efficient and economical electrocatalysts for oxygen evolution reaction（OER） represents the main bottleneck to unlocking a sustainable energy scenario based on elec trocataly tic water *** scale integration of three-dimensional（3D） porous heterostructure with highly dispersed active sites and good structural stability is ***,a dual template route is developed to construct the 3D porous SiO2/nitrogen-doped carbon（NC）/Co-carbon nano tubes（CNTs） hetero ***,the hard template（SiO2nano spheres） contributes to 3D porous structure,increases the specific surface area,and promotes the contact area of the *** the same time,the soft template（basic zinc carbonate） can control the growth of 1D CNTs and facilitate the exposure of the active ***,3D porous SiO2/NC/Co-CNTs hetero structure inherits highly dispersed Co nanoparticles coated by *** conductive channels and abundant N hetero atoms doping are reasonably constructed by a dual template ***,SiO2/NC/Co-CNTs catalyst provides an extraordinary activity for the OER in alkaline media,with a low overpotential of 298 mV at a current density of 10 mA·***,SiO2/NC/Co-CNTs hetero structure enables excellent long-term durability with a 10 mV decay in overpotential after 3000 cyclic voltammetry cycles,and 97% remain in current density over 20 *** is believed that this dual template strategy can provide a new and simple way to construct a highly dispersed active site in electrocatalysts.

关键词： Dual template High dispersion Porous heterostructure Conductive channels Oxygen evolution reaction

Dynamical localization in a non-Hermitian Floquet synthetic system

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Chinese Physics B 2024年第5期33卷 147-151页

作者：可汗张嘉明霍良赵文垒 school of science Jiangxi University of Science and TechnologyGanzhou 341000China school of Information Engineering Jiangxi University of Science and TechnologyGanzhou 341000China

We investigate the non-Hermitian effects on quantum diffusion in a kicked rotor model where the complex kicking potential is quasi-periodically modulated in the time *** synthetic space with arbitrary dimension can be created by incorporating incommensurate frequencies in the quasi-periodical *** the Hermitian case,strong kicking induces the chaotic diffusion in the four-dimension momentum space characterized by linear growth of mean *** find that the quantum coherence in deep non-Hermitian regime can effectively suppress the chaotic diffusion and hence result in the emergence of dynamical ***,the extent of dynamical localization is dramatically enhanced by increasing the non-Hermitian ***,the quasi-energies become complex when the non-Hermitian parameter exceeds a certain threshold *** quantum state will finally evolve to a quasi-eigenstate for which the imaginary part of its quasi-energy is large *** exponential localization length decreases with the increase of the non-Hermitian parameter,unveiling the underlying mechanism of the enhancement of the dynamical localization by nonHermiticity.

关键词： Floquet system non-Hermitian physics dynamical localization

维普期刊数据库

A comprehensive analysis of DAC-SDC FPGA low power object detection challenge

在线全文

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第8期67卷 300-320页

作者： Jingwei ZHANG Guoqing LI Meng ZHANG Xinye CAO Yu ZHANG Xiang LI Ziyang CHEN Jun YANG school of Electronics science and Engineering Southeast University

The lower power object detection challenge(LPODC) at the IEEE/ACM Design Automation Conference is a premier contest in low-power object detection and algorithm(software)-hardware co-design for edge artificial intelligence, which has been a success in the past five years. LPODC focused on designing and implementing novel algorithms on the edge platform for object detection in images taken from unmanned aerial vehicles(UAVs), which attracted hundreds of teams from dozens of countries to participate. Our team SEUer has been participating in this competition for three consecutive years from 2020 to 2022 and obtained sixth place respectively in 2020 and 2021. Recently, we achieved the championship in 2022. In this paper, we presented the LPODC for UAV object detection from 2018 to 2022, including the dataset, hardware platform,and evaluation method. In addition, we also introduced and discussed the details of methods proposed by each year's top three teams from 2018 to 2022 in terms of network, accuracy, quantization method, hardware performance, and total score. Additionally, we conducted an in-depth analysis of the selected entries and results, along with summarizing representative methodologies. This analysis serves as a valuable practical resource for researchers and engineers in deploying the UAV application on edge platforms and enhancing its feasibility and reliability. According to the analysis and discussion, it becomes evident that the adoption of a hardware-algorithm co-design approach is paramount in the context of tiny machine learning(TinyML).This approach surpasses the mere optimization of software and hardware as separate entities, proving to be essential for achieving optimal performance and efficiency in TinyML applications.

关键词： tiny machine learning object detection convolutional neural networks algorithm-hardware co-design low power field programmable gate array

同方期刊数据库

Interface interaction between SiO_(2) and magnetite under high temperature:particle migration and inhibition mechanism

在线全文

学校读者我要写书评

暂无评论

Journal of Iron and Steel Research International 2024年第3期31卷 561-572页

作者： Yao-zu Wang Jian-liang Zhang Qiang Cheng Hui-qing Jiang Zheng-jian Liu Yu-bo Tan school of Intelligent science and Technology University of Science and Technology BeijingBeijing 100083China school of Metallurgical and Ecological Engineering University of Science and Technology BeijingBeijing 100083China school of Advanced Engineering University of Science and Technology BeijingBeijing 100083China

Silicon is one of the main gangue components in iron ore,usually in the form of quartz and *** studies have shown that SiO_(2) has a two-sided effect on the consolidation of pellets during high-temperature oxidation roasting of ***,it is very difficult to capture the structural evolution and migration mechanisms during high-tem-perature roasting process by existing experimental ***,the influence of SiO_(2) on the consolidation behavior of magnetite was studied through a series of roasting experiments and molecular dynamic *** results show that the consolidation index and particle growth index decrease with the increase in SiO_(2) content in the *** 1573 K,the liquid phase promotes the recrystallization growth of hematite at high *** dynamic study shows that it is difficult for quartz SiO_(2) to form sintering neck with Fe_(2)O_(3).When the calcination temperature is higher than 1400 K,the Fe_(2)O_(3)-Fe_(2)SiO_(4) system produces a considerable sintering neck structure after *** atomic migration ability of Fe_(2)SiO_(4) is much higher than that of Fe_(2)O_(3).The higher atomic migration ability of Fe_(2)SiO_(4) is the main reason for the formation of the sintering neck.

关键词： Sintering neck Crystal growth Consolidation Molecular dynamics SiO_(2)

Prescribed-time stabilization and inverse optimal control of stochastic high-order nonlinear systems

维普期刊数据库评论

在线全文

维普期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第2期67卷 144-156页

作者： Ran LIU Hui WANG Wuquan LI school of Mathematics and Statistics science Ludong University

This paper investigates the prescribed-time state-feedback stabilization and prescribed-time inverse optimality problems for stochastic high-order nonlinear systems. First, a time-varying controller is designed by developing scaled quartic Lyapunov functions, which can guarantee that the system has a unique strong solution almost surely on the prescribed interval for any system initial conditions and that the states and the control converge to the origin in a mean-square form within the prescribed time. Then, the controller is redesigned to address the problem of prescribed-time inverse optimal mean-square stabilization. Finally,a concrete example is provided to confirm the efficiency of the proposed design schemes.

关键词： stochastic high-order nonlinear systems prescribed-time stabilization the scaled design inverse optimality

Fixed-time stabilization of output-constrained stochastic high-order nonlinear systems

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

science China(Information sciences) 2024年第4期67卷 5-20页

作者： Ruiming XIE Shengyuan XU Nanjing University of science and Technology school of Automation

In this study, the fixed-time stabilization problem of stochastic high-order nonlinear systems with output constraint and high-order and low-order nonlinearities is addressed. A new coordinate transformation is employed to directly convert output-constrained stochastic systems into an equivalent unconstrained *** fully extracting the characteristics of system nonlinearities and using the stochastic fixed-time stability theorem, a new design and analysis method is constructed to guarantee that the trivial solution of the closed-loop system is stochastically fixed-time stable while fulfilling the output constraint.

关键词： stochastic high-order nonlinear system outputconstraint high-order and low-order nonlinearity fixed-timestabilization finite-time stabilization

Advanced Algorithm for Parameters Estimation of Negative Binomial Distribution with High Dimensional Sparse Group Structure

在线全文

同方期刊数据库

学校读者我要写书评

暂无评论

Journal of Systems science & Complexity 2024年第5期37卷 2173-2195页

作者： LI Meiqi JIN Baisuo school of Management University of Science and Technology of China

Negative binomial regression is a powerful technique for modeling count data, particularly when dealing with overdispersion. However, estimating the parameters for large-dimensional sparse models is challenging due to the complexity of optimizing the mean and dispersion parameter of the negative binomial distribution. To address this issue, the authors propose a novel approach that employs two iterations of the majorize-minimize(MM) algorithm, one for estimating the dispersion parameter and the other for estimating the mean parameters. These approaches improve the convergence speed and stability of the algorithm. The authors also use group penalty for variable selection, which enhances the accuracy and efficiency of the algorithm. The proposed method provides an explicit solution,simplifies the iteration process, and maintains good stability while ensuring algorithm ***, the authors apply the proposed algorithm to the zero-inflated model and demonstrate its promising predictive performance on specific data sets. The research has important implications for count data modeling and analysis in various fields, such as data mining, machine learning, and bioinformatics.

关键词： Group structure majorize-minimize (MM) negative binomial