Agents in reinforcement learning tasks may learn slowly in large or complex tasks - transfer learning is one technique to speed up learning by providing an informative prior. How to best enable transfer between tasks ...
详细信息
Reinforcement learning agents can successfully learn in a variety of difficult tasks. A fundamental problem is that they may learn slowly in complex environments, inspiring the development of speedup methods such as t...
详细信息
The next-generation of cloud computing will thrive on how effectively the infrastructure are instantiated and available resources utilized dynamically. Load balancing which is one of the main challenges in Cloud compu...
详细信息
The next-generation of cloud computing will thrive on how effectively the infrastructure are instantiated and available resources utilized dynamically. Load balancing which is one of the main challenges in Cloud computing, distributes the dynamic workload across multiple nodes to ensure that no single resource is either overwhelmed or underutilized. This can be considered as an optimization problem and a good load balancer should adapt its strategy to the changing environment and the types of tasks. This paper proposes a novel load balancing strategy using Genetic Algorithm (GA). The algorithm thrives to balance the load of the cloud infrastructure while trying minimizing the make span of a given tasks set. The proposed load balancing strategy has been simulated using the CloudAnalyst simulator. Simulation results for a typical sample application shows that the proposed algorithm outperformed the existing approaches like First Come First Serve (FCFS), Round Robing (RR) and a local search algorithm Stochastic Hill Climbing (SHC).
We propose a semi-supervised framework to handle diverse data formats or data with mixed-type attributes. Our preliminary results in clustering data with mixed numerical and categorical attributes show that the propos...
详细信息
Clustering data streams is a challenging problem that has received significant attention in the recent decade. In this paper, we address the hitherto inadequately addressed challenge of managing the output of stream c...
详细信息
Recent years have seen an increasing interest in clustering data comprising multiple domains or modalities, such as categorical, numerical and transactional, etc. This kind of data is sometimes found within the contex...
详细信息
The personal photo retrieval task at ImageCLEF 2012 is a pilot task for testing QBE-based retrieval scenarios in the scope of personal information retrieval. This pilot task is organized as two subtasks: the visual co...
详细信息
The personal photo retrieval task at ImageCLEF 2012 is a pilot task for testing QBE-based retrieval scenarios in the scope of personal information retrieval. This pilot task is organized as two subtasks: the visual concepts retrieval and the events retrieval. In this paper, we develop a framework of combining different visual features, EXIF data and similarity measures based on two clustering methods to retrieve the relevant images having similar visual concepts. We first analyze and select the effective visual features including color, shape, texture, and descriptor to be the basic elements of recognition. A flexible similarity measure is then given to achieve high precise image retrieval automatically. The experimental results show that the proposed framework can provide good effectiveness in distinct measures of evaluation.
The task of visual concept detection, annotation, and retrieval using Flickr photos at ImageCLEF 2012 was organized as two subtasks: concept annotation and concept retrieval. In this paper, we present the effort of KI...
详细信息
The task of visual concept detection, annotation, and retrieval using Flickr photos at ImageCLEF 2012 was organized as two subtasks: concept annotation and concept retrieval. In this paper, we present the effort of KIDS lab for the two subtasks. The proposed approaches combine various visual and textual features, dimension reduction methods, the random forest classification models, and the semi-supervised learning strategy. For the concept annotation subtask, the annotation results show that combination of tags and visual features outperforms visual-only features while using the same classification model. The results also show that semi-supervised learning is not superior to supervised learning in this subtask. Further, it does not seem able to gain more advantage on F-measure when more different visual features were used. For the concept retrieval task, the results illustrate that the textual features contain much richer informatics than visual features in general retrieved concepts.
Measuring semantic relatedness plays an important role in information retrieval and Natural Language Processing. However, little attention has been paid to measuring semantic relatedness between named entities, which ...
详细信息
暂无评论