ARTÍCULO
TITULO

The Sample Complexity of Pattern Classification with Neural Networks: The Size of the Weights is More Important than the Size of the Network

Bartlett    
P L    

Resumen

No disponible

 Artículos similares

       
 
Simona Elena Avram, Bianca Violeta Birle, Lucian Barbu Tudoran, Gheorghe Borodi and Ioan Petean    
Used water treatment is one of the most important aspects of environmental protection regarding industrial processes. Particulate matter dispersions affect water parameters; for example, increased pH values such as 10.21 are found for used floor tile wat... ver más
Revista: Water

 
Zhuofan Xu, Jing Yan, Guoqing Sui, Yanze Wu, Meirong Qi, Zilong Zhang, Yingsan Geng and Jianhua Wang    
High-voltage circuit breakers (HVCBs) handle the important tasks of controlling and safeguarding electricity networks. In the case of insufficient data samples, improving the accuracy of the traditional HVCB mechanical fault diagnosis method is difficult... ver más
Revista: Applied Sciences

 
Qi Ping, Shiwei Wu, Xiangyang Li, Yijie Xu, Jing Hu and Shijia Sun    
The aim of this study was to examine the effects of sandstone ring specimens with different inner diameters on dynamic compression mechanical characteristics after dry and wet circulation. To carry out our study, we subjected a sandstone ring specimen wi... ver más
Revista: Applied Sciences

 
Meng Bi, Xianyun Yu, Zhida Jin and Jian Xu    
In this paper, we propose an Iterative Greedy-Universal Adversarial Perturbations (IGUAP) approach based on an iterative greedy algorithm to create universal adversarial perturbations for acoustic prints. A thorough, objective account of the IG-UAP metho... ver más
Revista: Applied Sciences

 
Baoyu Fan, Han Ma, Yue Liu and Xiaochen Yuan    
With the growth of data in the real world, datasets often encounter the problem of long-tailed distribution of class sample sizes. In long-tailed image recognition, existing solutions usually adopt a class rebalancing strategy, such as reweighting based ... ver más
Revista: Applied Sciences