Redirigiendo al acceso original de articulo en 19 segundos...
Inicio  /  Applied Sciences  /  Vol: 9 Par: 12 (2019)  /  Artículo
ARTÍCULO
TITULO

Efficient Weights Quantization of Convolutional Neural Networks Using Kernel Density Estimation based Non-uniform Quantizer

Sanghyun Seo and Juntae Kim    

Resumen

Convolutional neural networks (CNN) have achieved excellent results in the field of image recognition that classifies objects in images. A typical CNN consists of a deep architecture that uses a large number of weights and layers to achieve high performance. CNN requires relatively large memory space and computational costs, which not only increase the time to train the model but also limit the real-time application of the trained model. For this reason, various neural network compression methodologies have been studied to efficiently use CNN in small embedded hardware such as mobile and edge devices. In this paper, we propose a kernel density estimation based non-uniform quantization methodology that can perform compression efficiently. The proposed method performs efficient weights quantization using a significantly smaller number of sampled weights than the number of original weights. Four-bit quantization experiments on the classification of the ImageNet dataset with various CNN architectures show that the proposed methodology can perform weights quantization efficiently in terms of computational costs without significant reduction in model performance.

 Artículos similares

       
 
Ying Lv, Yuxin Wang, Xiaokai Zhang and Dasheng Zhang    
The efficient utilization of water resources is the key to ensuring sustainable development. Due to the complex relationship between resource utilization and economy and the environment, there are positive societal effects from a scientific and precise a... ver más
Revista: Water

 
Maryam Torkashvand, Aminreza Neshat, Saman Javadi, Hossein Yousefi and Ronny Berndtsson    
Vulnerability maps of groundwater provide an efficient means of identifying environmental trends and prioritizing regions for prevention plans. The GIS-based DRASTIC method, however, does not consider the impact of contamination, so there is a need to mo... ver más
Revista: Water

 
Niousha Ghannad and Kalpdrum Passi    
Currently, video and digital images possess extensive utility, ranging from recreational and social media purposes to verification, military operations, legal proceedings, and penalization. The enhancement mechanisms of this medium have undergone signifi... ver más
Revista: Algorithms

 
Yanjun Zhang, Shancheng Cao, Bintuan Wang and Zhiping Yin    
High-precision operational flight loads are essential for monitoring fatigue of individual aircraft and are usually determined by flight parameters. To tackle the nonlinear relationship between flight loads and flight parameters for more accurate predict... ver más
Revista: Applied Sciences

 
Luzhou Liu, Xiaoxia Zhang, Yingwei Li and Zhinan Xu    
Accurate segmentation of skin lesions is still a challenging task for automatic diagnostic systems because of the significant shape variations and blurred boundaries of the lesions. This paper proposes a multi-scale convolutional neural network, REDAUNet... ver más
Revista: Applied Sciences