This paper is concerned with solution of the consistent fundamental matrix estimation in a quadratic measurement error model. First an extended system for determining the estimator is proposed, and an efficient implem...
详细信息
We systematically propose a dual-phase algorithm, DualRank, to mine the optimal profit in retailing market. DualRank algorithm has two major phases which are called mining general profit phase and optimizing profit ph...
详细信息
ETL tools are responsible for the extraction of data from sources, their cleansing and loading into a target data warehouse. However, nowadays, the design and development of ETL processes are performed in an in-house ...
详细信息
Mobile ambients is a process calculus for modeling mobile agents in wide-area networks. It has important theoretical and practical values in studying concurrent and mobile computation as well as the security of intera...
详细信息
The use of the Internet raises serious behavioural issues regarding, for example, security and the interaction among agents that may travel across links. Model-building such interactive systems is one of the biggest c...
详细信息
Under the framework of LPU (learning from positive data and unlabeled data), this paper originally proposes a three-step algorithm. First, Co-Training is employed for filtering out the "suspect positive" dat...
详细信息
In this paper, a relatively flexible filter called extended bilateral filter is proposed, by which some particular filters can be designed via selecting an appropriate pixel of interest (POI) and defining a kernel for...
详细信息
Fourier-Mellin transform (FMT) is frequently used in content-based image retrieval and digital image watermarking. This paper extends the application of FMT into image registration and proposes an improved registratio...
详细信息
Q-learning is an effective model-free reinforcement learning algorithm. However, Q-learning is centralized and competent only for single agent learning but not multi-agent learning because in later case the size of st...
详细信息
Q-learning is an effective model-free reinforcement learning algorithm. However, Q-learning is centralized and competent only for single agent learning but not multi-agent learning because in later case the size of state-action space is huge and will grow exponentially with the number of agents increasing. In the paper we present a distributed Q-learning algorithm to solving this problem. In our algorithm, the tasks of learning optimal action policy are distributed to each agent in team but not a central agent. In order to reduce the size of action-state space of multi-agent team we introduce a state-action space sharing strategy of agent team, through which one agent in team can use the states already explored by other agents before and need not take time to explore these states again. Additionally, our algorithm has the ability to allocate sub-goals dynamically among agents according to environment changing, which can make agent team coordinate more efficiently. Experiments show the efficiency of our algorithm when it is applied to the benchmark problem of predator-prey pursuit game, also called pursuit game, in which a team of predators coordinate to capture a prey.
CP-networks provide a convenient means for expressing preferences in reasoning, but it is not good at handling preferences with hard constraints. The paper proposes a new approach, which transforms the CP-network with...
详细信息
CP-networks provide a convenient means for expressing preferences in reasoning, but it is not good at handling preferences with hard constraints. The paper proposes a new approach, which transforms the CP-network with hard constraints into one constraint hierarchy, therefore one could process preferences and constraints in a single formalism with fruitful constraint solving algorithms. Furthermore, illustrates it with some examples, proves that the transformation preserves the ceteris paribus property and presents some complexity results. Finally compares it with related work and concludes the paper.
暂无评论