检索结果-内蒙古大学图书馆

International Conference on Computational Science (ICCS)

作者： Menouer, Tarek Baarir, Souheib Paris Nanterre Univ CNRS UMR 7606 Lab LIP6 Paris France LRDE Lab Kremlin Bicltre France

Exploiting multi-core architectures is a way to tackle the CPU time consumption when solving SAT-isfiability (SAT) problems. Portfolio is one of the main techniques that implements this principle. It consists in making several solvers competing, on the same problem, and the winner will be the first that answers. In this work, we improved this technique by using a learning schema, namely the Exploration Exploitation using Exponential weight (EXP3), that allows smart resource allocations. Our contribution is adapted to situations where we have to solve a bench of SAT instances issued from one or several sequence of problems. Our experiments show that our approach achieves good results. (C) 2017 The Authors. Published by Elsevier B.V. Peer-review under responsibility of the scientific committee of the International Conference on Computational Science

关键词： Portfolio SATisfiability boolean learning algorithm Parallelization

来源：评论

学校读者我要写书评

暂无评论

learning of Audiovisual Integration

Learning of Audiovisual Integration

引用

IEEE International Conference on Development and learning (ICDL)

作者： Yan, Rujiao Rodemann, Tobias Wrede, Britta Univ Bielefeld Res Inst Cognit & Robot CoR Lab D-33594 Bielefeld Germany Honda Res Inst Europe GmbH D-63073 Offenbach Germany

ISBN: (纸本)9781612849904

We present a system for learning audiovisual integration based on temporal and spatial coincidence. The current sound is sometimes related to a visual signal that has not yet been seen, we consider this situation as well. Our learning algorithm is tested in online adaptation of audio-motor maps. Since audio-motor maps are not reliable at the beginning of the experiment, learning is bootstrapped using temporal coincidence when there is only one auditory and one visual stimulus. In the course of time, the system can automatically decide to use both spatial and temporal coincidence depending on the quality of maps and the number of visual sources. We can show that this audiovisual integration can work when more than one visual source appears. The integration performance does not decrease when the related visual source has not yet been spotted. The experiment is executed on a humanoid robot head.

关键词： Robot kinematics Tracking audio signal processing audio-motor maps audio-visual integration learning bootstrapped learning humanoid robot head humanoid robots learning algorithm robot vision spatial coincidence statistical analysis temporal coincidence visual signal

来源：评论

学校读者我要写书评

暂无评论

Multi-Agent Reinforcement learning with Information-sharing Constrained Policy Optimization for Global Cost Environment 22

Multi-Agent Reinforcement Learning with Information-sharing ...

引用

22nd World Congress of the International Federation of Automatic Control (IFAC)

作者： Okawa, Yoshihiro Dan, Hayato Morita, Natsuki Ogawa, Masatoshi Fujitsu Ltd Artificial Intelligence Lab Kawasaki Kanagawa Japan

ISBN: (纸本)9781713872344

Multi-agent Reinforcement learning (MARL) is a machine learning method that solves problems by using multiple learning agents in a data-driven manner. Because of the advantage of utilizing multiple agents simultaneously, MARL has become an efficient solution to large-scale problems in a wide range of fields. However, as with general single-agent reinforcement learning, MARL requires trial and error to acquire the appropriate policies for each agent in the learning process. Therefore, how to guarantee performance and constraint satisfaction in MARL is a critical issue for application to real-world problems. In this study, we propose an Information-sharing Constrained Policy Optimization (IsCPO) method for MARL that guarantees constraint satisfaction during learning. In detail, IsCPO sequentially updates the policies of multiple agents in random order while sharing information of the surrogate costs and KL-divergence for evaluating the current and updated policies to the next agent. In addition, if there are no candidates of policies to be updated in accordance with the shared information, IsCPO skips updating the policies of the rest of the agents until the next iteration. As a result, IsCPO makes it possible to acquire the individual suboptimal policies of agents, satisfying constraints on global costs related to the state of the environment and the actions from multiple agents. We also introduce a practical algorithm for IsCPO that simplifies its implementation by adopting several mathematical approximations. Finally, we show the validity and effectiveness through simulation results on a multiple cart-pole problem and base station sleep control problem in a mobile network.

关键词： Multi-agent reinforcement learning learning algorithm Constrained MDP Multi-agent system Base station sleep control Mobile network

来源：评论

学校读者我要写书评

暂无评论

learning a Propagation Complete Formula 1

引用

19th International Conference on the Integration of Constraint Programming, Artificial Intelligence, and Operations Research (CPAIOR)

作者： Kucera, Petr Charles Univ Prague Fac Math & Phys Dept Theoret Comp Sci & Math Log Prague Czech Republic

ISBN: (数字)9783031080111

ISBN: (纸本)9783031080111;9783031080104

Propagation complete formulas were introduced by Bordeaux and Marques-Silva (2012) as a possible target language for knowledge compilation. A CNF formula is propagation complete (PC) if for every partial assignment, the implied literals can be derived by unit propagation. Bordeaux and Marques-Silva (2012) proposed an algorithm for compiling a CNF formula into an equivalent PC formula which is based on incremental addition of so-called empowering implicates. In this paper, we propose a compilation algorithm based on the implicational structure of propagation complete formulas described by Kucera and Savicky (2020) and the algorithm for learning a definite Horn formula with closure and equivalence queries introduced by Atserias et al. (2021). We have implemented both approaches and compared them experimentally. Babka et al. (2013) showed that checking if a CNF formula admits an empowering implicate is an NP-complete problem. We propose a particular CNF encoding which allows us to use a SAT solver to check propagation completeness, or to find an empowering implicate.

关键词： propagation complete formula satisfiability consistency checking empowering clause learning algorithm

来源：评论

学校读者我要写书评

暂无评论

New algorithm to improve the learning performance of neural network through result-feedback

引用

Jisuanji Yanjiu yu Fazhan/Computer Research and Development 2004年第9期41卷 1488-1492页

作者： Wu, Yan Wang, Shou-Jue Dept. of Computer Sci. and Eng. Tongji Univ. Shanghai 200092 China Inst. of Semiconduct. and Info. Tech Tongji Univ. Shanghai 200092 China Lab. of Artificial Neural Networks Inst. of Semiconductors Chinese Acad. of Sciences Beijing 100083 China

The combination of input vector tuning with traditional weight tuning of back-propagation algorithm results in a new algorithm on the basis of result feedback (FBBP). This FBBP-based algorithm is an inner-and-outer layer learning method in which weight value renewing plays the dominating role with the assistance of input renewing. It minimizes the error function of neural network through the dual functioning of weight value and input vector value tuning. In the process neural network learning and training are estimated from an angle of result feedback along with the objective to effectively improve the learning performance of feed-forward neural network. Quite a few simulation experiments serve to make comparisons between the FBBP algorithm, the BP algorithm with momentum term, and a recently published algorithm that used weight updating method to speed up convergence. Experiment results are discussed. The results show that the new algorithm has the dual merits of quick training speed and good generalization capability. It proves to be a very effective learning method.

关键词： Generalization learning algorithm Neural network Result feedback

来源：评论

学校读者我要写书评

暂无评论

Diagnostic Neuro-Fuzzy System and Its learning in Medical Data Mining Tasks in Conditions of Uncertainty about Numbers of Attributes and Diagnoses

引用

AUTOMATIC CONTROL AND COMPUTER SCIENCES 2017年第6期51卷 391-398页

作者： Pliss, Iryna Perova, Iryna Kharkiv Natl Univ Radio Elect UA-61166 Kharkov Ukraine

Architecture and learning method for evolving diagnostic neuro-fuzzy-system for Medical Data Mining tasks in situation of uncertainty about quantities of attributes and diagnoses are proposed. Diagnostic neuro-fuzzy-system was approbated on data set, which present erosive ulcerous disease of the gastrointestinal tract and shown high quality of classification in condition of different quantity of input and output data.

关键词： Medical Data Mining classification fuzzification neuro-fuzzy system learning algorithm membership function

来源：评论

学校读者我要写书评

暂无评论

Tunable and Generic Problem Instance Generation for Multi-objective Reinforcement learning

Tunable and Generic Problem Instance Generation for Multi-ob...

引用

IEEE Symposium on Adaptive Dynamic Programming and Reinforcement learning (ADPRL)

作者： Garrett, Deon Bieger, Jordi Throisson, Kristinn R. Reykjavik Univ Iceland Inst Intelligent Machines Reykjavik Iceland Reykjavik Univ Reykjavik Iceland

ISBN: (纸本)9781479945528

A significant problem facing researchers in reinforcement learning, and particularly in multi-objective learning, is the dearth of good benchmarks. In this paper, we present a method and software tool enabling the creation of random problem instances, including multi-objective learning problems, with specific structural properties. This tool, called Merlin (for Multi-objective Environments for Reinforcement learning), provides the ability to control these features in predictable ways, thus allowing researchers to begin to build a more detailed understanding about what features of a problem interact with a given learning algorithm to improve or degrade the algorithm's performance. We present this method and tool, and briefly discuss the controls provided by the generator, its supported options, and their implications on the generated benchmark instances.

关键词： learning (artificial intelligence) software tools Merlin learning algorithm multiobjective environments for reinforcement learning multiobjective learning problem multiobjective reinforcement learning problem facing researcher random problem instance software tool structural property Benchmark testing Correlation Covariance matrices Generators Heuristic algorithms learning (artificial intelligence) Optimization Software Tools Neurofibromin 2 Benchmark testing Structural properties dynamos learning algorithms learning (artificial intelligence) Heuristic algorithms variance covariance matrix Covariance matrix

来源：评论

学校读者我要写书评

暂无评论

Representational Capabilities and learning of Bithreshold Neural Networks

Representational Capabilities and Learning of Bithreshold Ne...

引用

International Scientific Conference on Intellectual Systems of Decision-Making and Problems of Computational Intelligence (ISDMCI)

作者： Kotsovsky, Vladyslav Batyuk, Anatoliy Uzhgorod Natl Univ Uzhgorod Ukraine Lviv Polytech Natl Univ Lvov Ukraine

ISBN: (纸本)9783030542153;9783030542146

The paper deals with questions related to the ability of real-weighted bithreshold neurons and neural networks to solve the classification tasks. We study how many partitions of a finite set in n-dimensional vector space can be computed by using bithreshold neurons. The upper and lower bounds on the number of bithreshold dichotomies are proved. Our main theoretical result states that there exists Theta(m(n+1)) bithreshold dichotomies of the set of m points in general position in n-dimensional space. We also estimate the Vapnik-Chervonenkis dimension of the class of bithreshold neurons. The problem of the synthesis of 2-layer bithreshold neural network for binary classification is considered. We demonstrate that an arbitrary dichotomy of m points in general position in n-dimensional space can be realized by 2-layer neural network containing at most inverted right perpendicularm/(2n)inverted left perpendicular bithreshold neurons in hidden layer and a single output threshold neuron. The learning algorithm with computational complexity O(mn(2) + m(2)) is proposed for such networks. We give simulation results of the network performance on real data sets and discuss the influence of algorithm parameters on the quality of learning and the representational capabilities of bithreshold networks.

关键词： Bithreshold neuron Neural network Bithreshold network Classification learning algorithm

来源：评论

学校读者我要写书评

暂无评论

Formal Neuron Based on Adaptive Parametric Rectified Linear Activation Function and its learning 1

Formal Neuron Based on Adaptive Parametric Rectified Linear ...

引用

1st International Workshop on Digital Content and Smart Multimedia (DCSMart)

作者： Bodyanskiy, Yevgeniy Deineko, Anastasiia Pliss, Iryna Slepanska, Valeriia Kharkiv Natl Univ Radio Elect Control Syst Res Lab Kharkiv Ukraine Kharkiv Natl Univ Radio Elect Dept Artificial Intelligence Kharkiv Ukraine

The paper proposes an adaptive activation function (AdPReLU) for deep neural networks which is generalization of rectified unit family, differing by opportunity of online tuning its parameters during the learning process of neural network. The learning algorithm of formal neuron with adaptive activation function which is generalization of delta-rule and in which parameters of the function tune simultaneously with synaptic weights, based on error back-propagation is developed. The proposed algorithm of tuning is optimized for increasing of operating speed. Computational experiments confirm the effectiveness of the approach under consideration.

关键词： deep neural network adaptive activation function delta-rule synaptic weights rectified linear unit learning algorithm

来源：评论

学校读者我要写书评

暂无评论

learning BY PARALLEL FORWARD PROPAGATION

LEARNING BY PARALLEL FORWARD PROPAGATION

引用

INTERNATIONAL JOINT CONF ON NEURAL NETWORKS ( IJCNM-90 )

作者： ABE, S Hitachi Ltd Japan

The back-propagation algorithm is widely used for learning weights of multilayered neural networks. The major drawbacks however, are the slow convergence and lack of a proper way to set the number of hidden neurons. The author proposes a learning algorithm which solves the above problems. The weights between two layers are successively calculated, fixing other weights so that the error function, which is the square sum of the difference between the training data and the network outputs is minimised. Since the calculation results in solving a set of linearized equations, redundancy of the hidden neurons is judged by the singularity of the corresponding coefficient matrix. For the exclusive-OR and parity check circuits, excellence convergence characteristics are obtained, and the redundancy of the hidden neurons is checked by the singularity of the matrix

关键词： parallel forward propagation weights multilayered neural networks learning algorithm error function training data linearized equations redundancy hidden neurons singularity coefficient matrix exclusive-OR parity check circuits convergence characteristics learning systems neural nets parallel algorithms parallel architectures

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：