This paper presents a proposal for a fast on-line map analysis for the RTS game Planet Wars in order to define specialized strategies for an autonomous bot. This analysis is used to tackle two constraints of the game,...
详细信息
ISBN:
(数字)9781467311946
ISBN:
(纸本)9781467311939
This paper presents a proposal for a fast on-line map analysis for the RTS game Planet Wars in order to define specialized strategies for an autonomous bot. This analysis is used to tackle two constraints of the game, as featured in the Google AI Challenge 2010: the players cannot store any information from turn to turn, and there is a limited action time of just one second. They imply that the bot must analyze the game map quickly, to adapt its strategy during the game. Based in our previous work, in this paper we have evolved bots for different types of maps. Then, all bots are combined in one, to choose the evolved strategy depending on the geographical configuration of the game in each turn. Several experiments have been conducted to test the new approach, which outperforms our previous version, based on an off-line general training.
The continued increase in microprocessor clock frequency that has come from advancements in fabrication technology and reductions in feature size, creates challenges in maintaining both manufacturing yield rates and l...
详细信息
The continued increase in microprocessor clock frequency that has come from advancements in fabrication technology and reductions in feature size, creates challenges in maintaining both manufacturing yield rates and long-term reliability of devices. Methods based on defect detection and reduction may not offer a scalable solution due to cost of eliminating contaminants in the manufacturing process and increasing chip complexity. This paper proposes to use the inherent redundancy available in existing and future chip microarchitectures to improve yield and enable graceful performance degradation in fail-in-place systems. We introduce a new yield metric called performance averaged yield (Ypav) which accounts both for fully functional chips and those that exhibit some performance degradation. Our results indicate that at 250nm we are able to increase the Ypav of a uniprocessor with only redundant rows in its caches from a base value of 85% to 98% using microarchitectural redundancy. Given constant chip area, shrinking feature sizes increases fault susceptibility and reduces the base Ypav to 60% at 50nm, which exploiting microarchitectural redundancy then increases to 99.6%.
in shared-memory Chip Multiprocessor (CMP), shared data between different cores must be exchanged through the last-level-shared-cache and cache coherence must be maintained at the same time. As the number of cores inc...
详细信息
We present a model and a hardware architecture for the computation of bottom-up inherent visual attention for FPGA. The bottom-up inherent attention is generated including local energy, local orientation maps, and red...
详细信息
We present a model and a hardware architecture for the computation of bottom-up inherent visual attention for FPGA. The bottom-up inherent attention is generated including local energy, local orientation maps, and red-green and blue-yellow color opponencies. In this work, we describe the simplifications to parallelize and embed the model without significant accuracy loss. We also include feedback loops to adapt the weights of the features, depending on the target application.
Copyright protection and authentication have become increasingly more important in daily life. The digital watermark is one of the techniques invented to tackle this issue. In this paper, a digitally invisible waterma...
详细信息
ISBN:
(纸本)9781467355797
Copyright protection and authentication have become increasingly more important in daily life. The digital watermark is one of the techniques invented to tackle this issue. In this paper, a digitally invisible watermark is embedded in a QR code image by means of wavelet transform. In the embedding process, a binary image, logo, is transformed into a corresponding watermark and then embeded into a selected subband. The experimental results illustrated that, for all the cases considered in this paper is more robustness to attacks and as such it can serve as a viable copyright protection and authentication tool.
The European electrical transmission network is operated increasingly close to its operational limits due to market integration and increased feed-in by renewable energies. For this reason, innovative solutions for a ...
详细信息
We present a real-time technique for the spatiotemporal segmentation of color/depth movies. Images are segmented using a parallel Metropolis algorithm implemented on a GPU utilizing both color and depth information, a...
详细信息
Having large databases of annotated images is important for many applications in computer vision and computer graphics. Some of the largest databases of annotated images rely on user participation (as in Flickr, Label...
详细信息
Having large databases of annotated images is important for many applications in computer vision and computer graphics. Some of the largest databases of annotated images rely on user participation (as in Flickr, LabelMe or Peekaboom). In this paper we address the problem of performing semiautomatic object labeling as a way of providing new annotated images. Some current efforts in this direction provide bounding boxes as the annotations (i.e. OPTIMOL and Seville Systems). However, in this work we present an approach that relies on a boosting process to automatically create polygonal annotations for objects similar to those entered by users in tools such as LabelMe. In particular, we train single class boosting classifiers using local image features to perform the simultaneous object detection and segmentation. We validate our approach using different object classes from the LabelMe, the TUD and the Weizmann databases. Moreover, our experiments show that we are able to correctly annotate new data returned by internet search engines.
GPGPU has been widely used in recent years in both academia and industry. Many research for benchmarks on GPUs were reported to achieve over 100 times speedup, however, due to the high overhead of data transfer betwee...
详细信息
In the article we describe the approach to parallel implementation of elementary operations for textual data categorization. In the experiments we evaluate parallel computations of similarity matrices and k-means algo...
详细信息
In the article we describe the approach to parallel implementation of elementary operations for textual data categorization. In the experiments we evaluate parallel computations of similarity matrices and k-means algorithm. The test datasets have been prepared as graphs created from Wikipedia articles related with links. W also present the approach to computing pairs of eigenvectors and eigenvalues for visualizations of the datasets. The implemented basic operations: computing similarity matrix, data clustering and spectral analysis have been used in our system for visualization of the Wikipedia categories on SOM as well as in a system for categorization search results in Wikipedia.
暂无评论