检索结果-内蒙古大学图书馆

8th Catalan Conference on Artificial Intelligence

作者： Sapena, Oscar Onaindia, Eva Univ Politecn Valencia Dept Sistemas Informat & Computac Valencia 46022 Spain

ISBN: (纸本)9781586035600

In this paper we present a novel planning approach based on well known techniques such as goal decomposition and heuristic planning aimed at working in highly dynamic environments with time constraints Our contribution is a domain independent planner to incrementally generate plans under a deliberative frame work for reactive domains The planner follows the anytime principles i e a first solution plan can be quickly computed and the quality of the solution is improved as time is available Moreover the fist computation of the sequential actions allows the plan to start its execution before it is totally generated thus giving rise to a highly reactive planning system

关键词： On line planning anytime algorithms

来源：评论

学校读者我要写书评

暂无评论

anytime learning and adaptation of structured fussy behaviors

引用

ADAPTIVE BEHAVIOR 1997年第3-4期5卷 281-315页

作者： Bonarini, A POLITECN MILAN DIPARTIMENTO ELETTR & INFORMAZARTIFICIAL INTELLIGENCE & ROBOT PROJECTI-20133 MILANITALY

We present an approach to support effective learning and adaptation of behaviors for autonomous agents with reinforcement learning algorithms. These methods can identify control systems that optimize a reinforcement program, which is, usually, a straightforward representation of the designer's goals. Reinforcement learning algorithms usually are too slow to be applied in real time on embodied agents, although they provide a suitable way to represent the desired behavior. We have tackled three aspects of this problem: the speed of the algorithm, the learning procedure, and the control system architecture. The learning algorithm we have developed includes features to speed up learning, such as niche-based learning, and a representation of the control modules in terms of fuzzy rules that reduces the search space and improves robustness to noisy data. Our learning procedure exploits methodologies such as learning from easy missions and transfer of policy from simpler environments to the more complex. The architecture of our control system is layered and modular, so that each module has a low complexity and can be learned in a short time. The composition of the actions proposed by the modules is either learned or predefined. Finally, we adopt an anytime learning approach to improve the qualify of She control system on-line and to adapt it to dynamic environments. The experiments we present in this article concern learning to reach another moving agent in a real, dynamic environment that includes nontrivial situations such as that in which the moving target is faster than the agent and that in which the target is hidden by obstacles.

关键词： reinforcement learning autonomous agents fuzzy control hierarchical behaviors anytime learning anytime algorithms

来源：评论

学校读者我要写书评

暂无评论

Document Recognition Without Strong Models

Document Recognition Without Strong Models

引用

11th International Conference on Document Analysis and Recognition (ICDAR)

作者： Baird, Henry S. Lehigh Univ Comp Sci & Engn Dept Bethlehem PA 18015 USA

ISBN: (纸本)9780769545202

Can a high-performance document image recognition system be built without detailed knowledge of the application? Having benefited from the statistical machine-learning revolution of the last twenty years, our architectures rely less on hand-crafted special-case rules and more on models trained on labeled-sample data sets. But urgent questions remain. When we can't collect (and label) enough real training data, does it help to complement them with data synthesized using generative models? Is it ever completely safe to rely on synthetic data? If we can't manage to train (or craft) a single complete, near-perfect, application-specific "strong" model to drive recognition, can we make progress by combining several imperfect or incomplete "weak" models? Can recognition that is carried out jointly over weak models perform optimally while still running fast? Can a recognizer automatically pick a strong model of its input? Must we always pre-train models for every kind ("style") of input expected, or can a recognizer adapt to unknown styles? Can weak models adapt autonomously, growing stronger and so driving accuracy higher, without any human intervention? Can one model "criticize"-and then proceed to correct-other models, even while it is being criticized and corrected in turn by them? After twenty-five years of research on these questions we have partial answers, many in the affirmative: in addition to promising laboratory demonstrations, we can take pride in successful applications. I'll illustrate the evolution of the state of the art with concrete examples, and point out open problems.

关键词： Rule-based recognition model-driven recognition learning models synthetically generated data strong versus weak models joint recognition style-conscious recognition adaptive recognition anytime algorithms whole-book recognition

来源：评论

学校读者我要写书评

暂无评论

High-confidence control: Ensuring reliability in high-performance real-time systems 1

High-confidence control: Ensuring reliability in high-perfor...

引用

1st International IEEE Symposium on Intelligent Systems

作者： Samad, T Honeywell Automat & Control Solut Minneapolis MN 55418 USA

ISBN: (纸本)0780376013

Technology transfer is an especially difficult proposition for real-time control. To facilitate it, we need to complement the "high performance" orientation of control research with an emphasis on demonstrating "high confidence" in real-time implementation. Two particular problems are discussed and recent research directed at their solutions presented. First, the use of anytime algorithms requires dynamic resource management technology that is not generally available today in real-time systems. Second, complex algorithms have unpredictable computational characteristics that nevertheless need to be modeled;statistical verification is suggested as a possible approach. In both cases, a synthesis of control engineering and computer science is required if effective solutions are to be devised.

关键词： theory/practice gap verification and validation anytime algorithms probabilistic verification

来源：评论

学校读者我要写书评

暂无评论

Methods of Weighted Combination for Text Field Recognition in a Video Stream 12

Methods of Weighted Combination for Text Field Recognition i...

引用

12th International Conference on Machine Vision (ICMV)

作者： Petrova, Olga Bulatov, Konstantin Arlazarov, Vladimir L. Russian Acad Sci Fed Res Ctr Comp Sci & Control Moscow Russia Smart Engines Serv LLC Moscow Russia Moscow Inst Phys & Technol MIPT Moscow Russia

ISBN: (纸本)9781510636446

Due to a noticeable expansion of document recognition applicability, there is a high demand for recognition on mobile devices. A mobile camera, unlike a scanner, cannot always ensure the absence of various image distortions, therefore the task of improving the recognition precision is relevant. The advantage of mobile devices over scanners is the ability to use video stream input, which allows to get multiple images of a recognized document. Despite this, not enough attention is currently paid to the issue of combining recognition results obtained from different frames when using video stream input. In this paper we propose a weighted text string recognition results combination method and weighting criteria, and provide experimental data for verifying their validity and effectiveness. Based on the obtained results, it is concluded that the use of such weighted combination is appropriate for improving the quality of the video stream recognition result.

关键词： mobile recognition video stream optical character recognition anytime algorithms

来源：评论

学校读者我要写书评

暂无评论

An Improvement Heuristic Based on Variable Neighborhood Search for a Dynamic Orienteering Problem 1

引用

21st European Conference on Evolutionary Computation in Combinatorial Optimization (EvoCOP)

作者： Le, Hoang Thanh Middendorf, Martin Shi, Yuhui Univ Leipzig Inst Comp Sci Swarm Intelligence & Complex Syst Grp Leipzig Germany Southern Univ Sci & Technol Comp Sci & Engn Shenzhen Peoples R China

ISBN: (数字)9783030729042

ISBN: (纸本)9783030729035;9783030729042

The Dynamic Orienteering Problem (DOP) is studied where nodes change their value over time. An improvement heuristic that is based on Variable Neighborhood Search is proposed for the DOP. The new heuristic is experimentally compared with two heuristics that are based on state-of-the-art algorithms for the static Orienteering Problem. For the experiments several benchmark instances are used as well as instances that are generated from existing road networks. The results show that the new heuristic outperforms the other heuristics with respect to several evaluation criteria and different measures for run time. An additional experiment shows that the new heuristic can be easily adapted to become a standalone algorithm that does not need given initial solutions. The standalone version obtains better results than two state-of-the-art algorithms.

关键词： Dynamic optimization Neighborhood search anytime algorithms Routing problems

来源：评论

学校读者我要写书评

暂无评论

anytime Reasoning Mechanism for Conversational Agents

Anytime Reasoning Mechanism for Conversational Agents

引用

12th International Conference of the Catalan-Association-for-Artificial-Intelligence (CCIA)

作者： Morveli-Espinoza, Mariela Puyol-Gruart, Josep CSIC Spanish Sci Res Council Artificial Intelligence Res Inst IIIA Madrid Spain

ISBN: (纸本)9781607504658;9781607500612

When an agent receives a query from another agent, it tries to satisfy it by building an answer based on its current knowledge. Depending on the available time or the urgency of the requirement the agent can produce answers with different levels of quality. Answers can contain the best one, a provisional one because it can be improved later, or a conditional answer because the agent ignores some information needed to build the answer. Agents always depend on the availability of information obtained from perception or from the communication with other agents. We assume that in the real world normally is better to receive an answer with poor quality than no answer. The answer can be good enough for the receiver or the receiver can spend more time to wait for a better answer. Autonomy implies taking the best decision with the available information, avoiding blocking situations and no action. In this paper, we propose an architecture for deliberative agents using anytime like reasoning to produce better answers as time increases.

关键词： anytime algorithms progressive reasoning multi-agent systems partial deduction multiple-valued logic

来源：评论

学校读者我要写书评

暂无评论

anytime learning and classification for online applications 4

Anytime learning and classification for online applications

引用

4th International Conference on Active Media Technology

作者： Webb, Geoffrey I. Monash Univ Clayton Vic 3800 Australia

ISBN: (纸本)9781586036157

Many online applications of machine learning require fast classification and hence utilize efficient classifiers such as nave Bayes. However, outside periods of peak computational load, additional computational resources will often be available. anytime classification can use whatever computational resources may be available at classification time to improve the accuracy of the classifications made.

关键词： machine learning anytime algorithms anytime learning anytime classification

来源：评论

学校读者我要写书评

暂无评论

A Greedy anytime Algorithm for Sparse PCA 33

A Greedy Anytime Algorithm for Sparse PCA

引用

33rd Conference on Learning Theory (COLT)

作者： Holtzman, Guy Soffer, Adam Vilenchik, Dan Ben Gurion Univ Negev Beer Sheva Israel

The taxing computational effort that is involved in solving some high-dimensional statistical problems, in particular problems involving non-convex optimization, has popularized the development and analysis of algorithms that run efficiently (polynomial-time) but with no general guarantee on statistical consistency. In light of the ever-increasing compute power and decreasing costs, a more useful characterization of algorithms is by their ability to calibrate the invested computational effort with various characteristics of the input at hand and with the available computational resources. We propose a new greedy algorithm for the l(0)-sparse PCA problem which supports the calibration principle. We provide both a rigorous analysis of our algorithm in the spiked covariance model, as well as simulation results and comparison with other existing methods. Our findings show that our algorithm recovers the spike in SNR regimes where all polynomial-time algorithms fail while running in a reasonable parallel-time on a cluster.

关键词： Sparse PCA non-convex optimization anytime algorithms average case analysis

来源：评论

学校读者我要写书评

暂无评论

anytime Learning of Sum-Product and Sum-Product-Max Networks 11

Anytime Learning of Sum-Product and Sum-Product-Max Networks

引用

International Conference on Probabilistic Graphical Models

作者： Pawar, Swaraj Doshi, Prashant Univ Georgia Sch Comp THINC Lab Athens GA 30602 USA

Prominent algorithms for learning sum-product networks (SPN) and sum-product-max networks (SPMN) focus on learning models from data that deliver good modeling performance without regard to the size of the learned network. Consequently, the learned networks can get very large, which negatively impacts inference time. In this paper, we introduce anytime algorithms for learning SPNs and SPMNs. These algorithms generate intermediate but provably valid models whose performance progressively improves as more time and computational resources are allocated to the learning. They flexibly trade off good model performance with reduced learning time, offering the benefit that SPNs and SPMNs of small sizes (but with reduced likelihoods) can be learned quickly. We comprehensively evaluate the anytime algorithms on two testbeds and demonstrate that the network performance improves with time and reflects the expected performance profile of an anytime algorithm. We expect these anytime algorithms to become the default learning techniques for SPNs and SPMNs given their clear benefit over classical batch learning techniques.

关键词： anytime algorithms decision making flexible probabilistic graphical models

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：