**2016年年度应用** * 无需锻炼设备,每天只需几分钟时间 * 趣味成就和奖励不断鼓励你 * 基于《纽约时报杂志》报道的7分钟科学锻炼文章

热门内容

Deep Convolutional Neural Networks (CNNs) are a special type of Neural Networks, which have shown state-of-the-art results on various competitive benchmarks. The powerful learning ability of deep CNN is largely achieved with the use of multiple non-linear feature extraction stages that can automatically learn hierarchical representation from the data. Availability of a large amount of data and improvements in the hardware processing units have accelerated the research in CNNs and recently very interesting deep CNN architectures are reported. The recent race in deep CNN architectures for achieving high performance on the challenging benchmarks has shown that the innovative architectural ideas, as well as parameter optimization, can improve the CNN performance on various vision-related tasks. In this regard, different ideas in the CNN design have been explored such as use of different activation and loss functions, parameter optimization, regularization, and restructuring of processing units. However, the major improvement in representational capacity is achieved by the restructuring of the processing units. Especially, the idea of using a block as a structural unit instead of a layer is gaining substantial appreciation. This survey thus focuses on the intrinsic taxonomy present in the recently reported CNN architectures and consequently, classifies the recent innovations in CNN architectures into seven different categories. These seven categories are based on spatial exploitation, depth, multi-path, width, feature map exploitation, channel boosting and attention. Additionally, it covers the elementary understanding of the CNN components and sheds light on the current challenges and applications of CNNs.

0
36
下载
预览

最新内容

We consider evacuation from a finite two-dimensional (2D) square grid field by a metamorphic robotic system (MRS). An MRS is composed of anonymous memoryless modules. Each module of an MRS executes an identical distributed algorithm and moves autonomously while keeping the connectivity of modules. Since the modules are memoryless, an MRS utilizes its shape to remember the progress of execution. The number of available shapes that an MRS can form depends on the number of modules, which is thus an important complexity measure for a behavior of an MRS. In this paper, we investigate the minimum number of modules required to solve the evacuation problem with several conditions. First, we consider a rectangular field surrounded by walls with at least one exit and show that two modules are necessary and sufficient for evacuation from any rectangular field if the modules are equipped with a global compass, which allows the modules to have a common sense of direction. Then, we focus on the case where modules do not have a global compass and show that four (resp. seven) modules are necessary and sufficient for restricted (resp. any) initial states of an MRS. We also show that two modules are sufficient in the special case where an MRS is on a wall in an initial configuration. Finally, we extend these results to another type of fields, that is, mazes.

0
0
下载
预览

最新论文

We consider evacuation from a finite two-dimensional (2D) square grid field by a metamorphic robotic system (MRS). An MRS is composed of anonymous memoryless modules. Each module of an MRS executes an identical distributed algorithm and moves autonomously while keeping the connectivity of modules. Since the modules are memoryless, an MRS utilizes its shape to remember the progress of execution. The number of available shapes that an MRS can form depends on the number of modules, which is thus an important complexity measure for a behavior of an MRS. In this paper, we investigate the minimum number of modules required to solve the evacuation problem with several conditions. First, we consider a rectangular field surrounded by walls with at least one exit and show that two modules are necessary and sufficient for evacuation from any rectangular field if the modules are equipped with a global compass, which allows the modules to have a common sense of direction. Then, we focus on the case where modules do not have a global compass and show that four (resp. seven) modules are necessary and sufficient for restricted (resp. any) initial states of an MRS. We also show that two modules are sufficient in the special case where an MRS is on a wall in an initial configuration. Finally, we extend these results to another type of fields, that is, mazes.

0
0
下载
预览
父主题
Top