检索结果-内蒙古大学图书馆

ieee symposium Series on Computational Intelligence (SSCI)

作者： Harshal V Bharatia ACM Student Member Plano USA

ISBN: (纸本)9781728190495

An autonomous learning approach is presented here for expansive problem domains that may undergo frequent changes. It is hard to train and adapt learning-models to changes when the problem domain is very large. With the autonomous learning approach, a system performs knowledge refinement automatically by determining what can be improved and trains itself without explicit guidance to do so. It uses novel techniques to automatically create the learning-models and select an optimal model for each prediction. It automatically builds dynamic ensembles of models that incorporate specific improvisations, such as improvements based on past knowledge or specific trends reflected in the results, and overshadows sub-optimal portions of existing model. A reinforcement learning based model selector identifies which model is optimal for handling a request using a novel approach with automatically created hierarchical states. As a result, smart adaptive solutions that go beyond initial training become possible. This also alleviates the need for big complex monolithic models that require extensive training, automatically adapts to changes in the domain and offers better control over its performance. Experimental results show this approach learns quickly, adapts to changes very rapidly and performs quite well against prevalent learning methods.

关键词： Training learning systems Adaptation models Computational modeling reinforcement learning Switches Predictive models

来源：评论

学校读者我要写书评

暂无评论

adaptive Optimal Output Regulation of Time-Delay Systems via Measurement Feedback

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2019年第3期30卷 938-945页

作者： Gao, Weinan Jiang, Zhong-Ping Georgia Southern Univ Dept Elect & Comp Engn Allen E Paulson Coll Engn & Comp Statesboro GA 30460 USA NYU Dept Elect & Comp Engn Tandon Sch Engn Brooklyn NY 11201 USA

This brief proposes a novel solution to problems related to the measurement feedback adaptive optimal output regulation of discrete-time linear systems with input time-delay. Based on reinforcement learning and adaptive dynamic programming, an approximate optimal control policy is obtained via recursive numerical algorithms using online information. Convergence proofs for the proposed algorithms are given. Notably, the exact knowledge of the plant and the exosystem is not needed. The learned control policy is only a function of retrospective input and measurement output data. Theoretical analysis and an application to a grid-connected inverter show that the proposed methodologies serve as effective tools for solving adaptive and optimal output regulation problems.

关键词： Measurement feedback control optimal control output regulation reinforcement learning time-delay systems

来源：评论

学校读者我要写书评

暂无评论

An adaptive Model Management Strategy: Balancing Exploration and Exploitation

An Adaptive Model Management Strategy: Balancing Exploration...

引用

ieee symposium Series on Computational Intelligence (SSCI)

作者： Caie Hu Sanyou Zeng Changhe Li Mechanical Engineering and Electronic Information China University of Geoscience Wuhan China Automation and Hubei key Laboratory of Advanced Control and Intelligent Automation for Complex Systems China University of Geoscience Wuhan China

ISBN: (纸本)9781728190495

Model management is a critical component in data-driven surrogate-assisted evolutionary optimization. It is mainly used for selecting candidate samples to be evaluated using exact functions to balance the exploration and exploitation of algorithms. However, there are some potential limitations for typical infill sampling criteria. An adaptive model management strategy is proposed to overcome the limitations. It adaptively adjusts the selection probability of candidate samples, and avoids potentially unreliability and the burden of selecting parameters of typical infill sampling criteria. The comparison results on benchmark problems demonstrate the competitiveness of the strategy in solving data-driven optimization problems.

关键词： Adaptation models Toy manufacturing industry reinforcement learning Evolutionary computation Benchmark testing Linear programming Optimization

来源：评论

学校读者我要写书评

暂无评论

Resource Provisioning in Fog Computing through Deep reinforcement learning

Resource Provisioning in Fog Computing through Deep Reinforc...

引用

IFIP/ieee International symposium on Integrated Network Management

作者： José Santos Tim Wauters Bruno Volckaert Filip De Turck IDLab Ghent University - imec Gent Belgium

The massive growth of connected devices has made traditional cloud systems inadequate to sustain the scalability, mobility, and heterogeneous nature of the Internet of Things (oT). Distributed clouds have become a potential business opportunity for many service providers enabling the deployment of services on computational resources from the cloud up to the edge. However, challenges persist in fog-cloud infrastructures. One of them is known as Service Function Chaining (SFC), where providers benefit from network softwarization to create virtual chains of connected micro-services. Research has tackled SFC Allocation (SFCA) through theoretical modeling and heuristic algorithms, which often cannot cope with the dynamic behavior of the network. Recent works have addressed these challenges through Machine learning (ML), which can be capable of dynamically reconfiguring cloud-native service requirements over the continuum of virtual resources in next-generation networks. Thus, in this paper, a Deep reinforcement learning (DRL) approach is proposed for SFCA in Fog Computing focused on energy efficiency. Our agent learns about the best resource allocation decisions, focused on reducing costs from a previously presented Mixed-integer linear programming (MILP) formulation. Results show that our agent achieves comparable performance to state-of-the-art MILP formulations during dynamic use cases, obtaining 95% of request acceptance.

关键词： Training Radio frequency Cloud computing Service function chaining Heuristic algorithms Computational modeling Scalability

来源：评论

学校读者我要写书评

暂无评论

ISBI 2020 - 2020 ieee International symposium on Biomedical Imaging

ISBI 2020 - 2020 IEEE International Symposium on Biomedical ...

引用

17th ieee International symposium on Biomedical Imaging, ISBI 2020

ISBN: (纸本)9781538693308

The proceedings contain 424 papers. The topics discussed include: segmentation-based method combined with dynamic programming for brain midline delineation;automatic extraction and sign determination of respiratory signal in real-time cardiac magnetic resonance imaging;diffeomorphic smoothing for retinotopic mapping;deepseed: 3D squeeze-and-excitation encoder-decoder convolutional neural networks for pulmonary nodule detection;deblurring cataract surgery videos using a multi-scale deconvolutional neural network;automated hemorrhage detection from coarsely annotated fundus images in diabetic retinopathy;open-set OCT image recognition with synthetic learning;temporally adaptive-dynamic sparse network for modeling disease progression;and bone structures extraction and enhancement in chest radiographs via CNN trained on synthetic data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

reinforcement learning for adaptive Caching With dynamic Storage Pricing

引用

ieee JOURNAL ON SELECTED AREAS IN COMMUNICATIONS 2019年第10期37卷 2267-2281页

作者： Sadeghi, Alireza Sheikholeslami, Fatemeh Marques, Antonio G. Giannakis, Georgios B. Univ Minnesota Digital Technol Ctr Minneapolis MN 55455 USA Univ Minnesota Dept Elect & Comp Engn Minneapolis MN 55455 USA King Juan Carlos Univ Dept Signal Theory & Commun Madrid 28943 Spain

Small base stations (SBs) of fifth-generation (SG) cellular networks are envisioned to have storage devices to locally serve requests for reusable and popular contents by caching them at the edge of the network, close to the end users. The ultimate goal is to smartly utilize a limited storage capacity to serve locally contents that are frequently requested instead of fetching them from the cloud, contributing to a better overall network performance and service experience. To enable the SBs with efficient fetch-cache decision-making schemes operating in dynamic settings, this paper introduces simple but flexible generic time-varying fetching and caching costs, which are then used to formulate a constrained minimization of the aggregate cost across files and time. Since caching decisions per time slot influence the content availability in future slots, the novel formulation for optimal fetch-cache decisions falls into the class of dynamic programming. Under this generic formulation, first by considering stationary distributions for the costs as well as file popularities, an efficient reinforcement learning-based solver known as value iteration algorithm can be used to solve the emerging optimization problem. Later, it is shown that practical limitations on cache capacity can be handled using a particular instance of this generic dynamic pricing formulation. Under this setting, to provide a light-weight online solver for the corresponding optimization, the well-known reinforcement learning algorithm, Q-learning, is employed to find optimal fetch-cache decisions. Numerical tests corroborating the merits of the proposed approach wrap up the paper.

关键词： dynamic caching fetching dynamic programming value iteration Q-learning

来源：评论

学校读者我要写书评

暂无评论

Power Control for Wireless VBR Video Streaming: From Optimization to reinforcement learning

引用

ieee TRANSACTIONS ON COMMUNICATIONS 2019年第8期67卷 5629-5644页

作者： Ye, Chuang Gursoy, M. Cenk Velipasalar, Senem Syracuse Univ Dept Elect Engn & Comp Sci Syracuse NY 13244 USA

In this paper, we investigate the problem of power control for streaming variable bit rate (VBR) videos over wireless links. A system model involving a transmitter (e.g., a base station) that sends VBR video data to a receiver (e.g., a mobile user) equipped with a playout buffer is adopted, as used in dynamic adaptive streaming video applications. In this setting, we analyze power control policies considering the following two objectives: 1) the minimization of the transmit power consumption and 2) the minimization of the transmission completion time of the communication session. In order to play the video without interruptions, the power control policy should also satisfy the requirement in which the VBR video data is delivered to the mobile user without causing playout buffer underflow or overflows. A directional water-filling algorithm, which provides a simple and concise interpretation of the necessary optimality conditions, is identified as the optimal offline policy. Following this, two online policies are proposed for power control based on channel side information (CSI) prediction within a short time window. dynamic programming is employed to implement the optimal offline and the initial online power control policies that minimize the transmit power consumption in the communication session. Subsequently, reinforcement learning (RL)-based approach is employed for the second online power control policy. Through the simulation results, we show that the optimal offline power control policy that minimizes the overall power consumption leads to substantial energy savings compared with the strategy of minimizing the time duration of video streaming. We also demonstrate that the RL algorithm performs better than the dynamic programming-based online grouped water-filling (GWF) strategy unless the channel is highly correlated.

关键词： dynamic programming playout buffer underflow playout buffer overflow power control reinforcement learning variable bit rate (VBR) video video streaming

来源：评论

学校读者我要写书评

暂无评论

Output Feedback Q-learning Control for the Discrete-Time Linear Quadratic Regulator Problem

引用

ieee TRANSACTIONS ON NEURAL NETWORKS AND learning SYSTEMS 2019年第5期30卷 1523-1536页

作者： Rizvi, Syed Ali Asad Lin, Zongli Univ Virginia Charles L Brown Dept Elect & Comp Engn Charlottesville VA 22904 USA

Approximate dynamic programming (ADP) and reinforcement learning (RL) have emerged as important tools in the design of optimal and adaptive control systems. Most of the existing RL and ADP methods make use of full-state feedback, a requirement that is often difficult to satisfy in practical applications. As a result, output feedback methods are more desirable as they relax this requirement. In this paper, we present a new output feedback-based Q-learning approach to solving the linear quadratic regulation (LQR) control problem for discrete-time systems. The proposed scheme is completely online in nature and works without requiring the system dynamics information. More specifically, a new representation of the LQR Q-function is developed in terms of the input-output data. Based on this new Q-function representation, output feedback LQR controllers are designed. We present two output feedback iterative Q-learning algorithms based on the policy iteration and the value iteration methods. This scheme has the advantage that it does not incur any excitation noise bias, and therefore, the need of using discounted cost functions is circumvented, which in turn ensures closed-loop stability. It is shown that the proposed algorithms converge to the solution of the LQR Riccati equation. A comprehensive simulation study is carried out, which illustrates the proposed scheme.

关键词： Approximate dynamic programming (ADP) linear quadratic regulation (LQR) output feedback Q-learning reinforcement learning (RL)

来源：评论

学校读者我要写书评

暂无评论

Novel Scheme for Congestion Control in Cellular Networks Using Deep reinforcement learning and Markov Decision Process Models

Novel Scheme for Congestion Control in Cellular Networks Usi...

引用

2020 International Conference in Mathematics, Computer Engineering and Computer Science, ICMCECS 2020

作者： Arinze, Uchechukwu Bakpo, Francis Eneh, Agozie Longe, Olumide Department of Computer Science Enugu Nigeria Department of Information Systems Adamawa Yola Nigeria

ISBN: (数字)9781728131269

ISBN: (纸本)9781728131269

This research deals with the general issue of quality of service (QoS) provisioning and resource utilization in telecommunication networks. The issue requires that mobile network income be optimized while simultaneously satisfying QoS constraints that prevent getting into specific states and utilization of specific actions. However, supporting QoS requirements of different traffic types is more complicated due to the need to minimize two performance indicators - the probability of discarding a handover call and the probability of hindering a new call. Several approaches proposed recently try to provide efficient model-based solution to the problem by formulating it as an average reward neuro-dynamic programming (NDP) optimization problem together with decomposition function, but this is limited by Bellman's curse of dimensionality. In this paper, we proposed a novel hybrid optimization scheme to address the problem using Deep reinforcement learning (DRL), Markov Decision Process (MDP) and adaptive joint call admission control (AJCAC) respectively. In the proposed scheme, two classes of arrival traffic at the base station (BS) are considered;voice (real-time) and data (non-real-time) calls. Furthermore, traffic is classified as new and handoff according to the type of request. The scheme introduces an adaptive threshold value, which dynamically adjusts the network resources under high traffic intensity. In addition, the scheme introduces a learning agent whose state is described by an MDP. The MATLAB version 2010 software, OMNET++ simulator and SPSS will be used for data, numerical, algorithm simulation and modeling. Data analysis and simulation results will be carried out for performance evaluation of the proposed DQL-AJCAC scheme against existing models. © 2020 ieee.

关键词： reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

UCT-ADP Progressive Bias Algorithm for Solving Gomoku

UCT-ADP Progressive Bias Algorithm for Solving Gomoku

引用

ieee symposium Series on Computational Intelligence (SSCI)

作者： Cao, Xu Lin, Yanghao Fudan Univ Sch Data Sci Shanghai Peoples R China

ISBN: (纸本)9781728124858

We combine adaptive dynamic programming (ADP), a reinforcement learning method and UCB applied to trees (UCT) algorithm with a more powerful heuristic function based on Progressive Bias method and two pruning strategies for a traditional board game Gomoku. For the adaptive dynamic programming part, we train a shallow forward neural network to give a quick evaluation of Gomoku board situations. UCT is a general approach in MCTS as a tree policy. Our framework use UCT to balance the exploration and exploitation of Gomoku game trees while we also apply powerful pruning strategies and heuristic function to re-select the available 2-adjacent grids of the state and use ADP instead of simulation to give estimated values of expanded nodes. Experiment result shows that this method can eliminate the search depth defect of the simulation process and converge to the correct value faster than single UCT. This approach can be applied to design new Gomoku AI and solve other Gomoku-like board game.

关键词： adaptive dynamic programming monte carlo tree search gomoku exponential heuristic progressive bias

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：