In recent years hashing methods have attracted considerable attention. The main procedure of manifold hashing methods is to convert the high dimension features into binary codes and then use manifold distance to appro...
详细信息
2021 3rd international conference on computer modeling, simulation and algorithm(cmsa2021) widely covering computermodeling and Optimization Methods, simulation and Its Application, algorithm and Applied Mathematics ...
详细信息
2021 3rd international conference on computer modeling, simulation and algorithm(cmsa2021) widely covering computermodeling and Optimization Methods, simulation and Its Application, algorithm and Applied Mathematics is rescheduled to be held on July 4, 2021 via Tencent Meeting the in consideration of the current development of the Covid-19 epidemic.
The rapid development of recommender systems makes researchers pay more and more attention to the utilization of users39; subjective factors. Among various subjective factors, emotion plays an important role that ca...
详细信息
Based on practical application, this paper further discusses the database programming technology in computer software engineering. computer technology has developed to a certain extent and is still active in various f...
详细信息
In recent years, with the continuous upgrading of terrorist activities, the application of imaging radar has expanded to the detection of hidden targets, such as target detection:behind the wall, mine detection, dange...
详细信息
The analysis of approaches to assessing the vulnerability of complex network systems and indicators used to measure the effect of external influences on the nodes and connections of the network is carried out. The pro...
详细信息
The use of terrestrial laser is increasing in the field of architecture, especially in the design and construction of indoor space, and the point clouds generated by laser scanning is increasingly needed for assistanc...
详细信息
Abstarct. The indoor positioning based on wireless sensor networks (WSN) has become one of the research hotpots. However, the NLOS propagation of the distance signals greatly challenges the accuracy and robustness of ...
详细信息
The exploration of custom deep neural network (DNN) based accelerators for highly energy constrained edge devices with on-device intelligence is gaining traction in the research community. Despite the superior through...
详细信息
ISBN:
(纸本)9781665419130
The exploration of custom deep neural network (DNN) based accelerators for highly energy constrained edge devices with on-device intelligence is gaining traction in the research community. Despite the superior throughout and performance of custom accelerators as compared to CPUs or GPUs, the energy efficiency and versatility of state-of-the-art DNN accelerators is constrained due to the limited scope of monolithic architectures, where the entire accelerator executes only one model at any given time. In this paper, a multi-voltage domain heterogeneous DNN accelerator architecture is proposed that simultaneously executes multiple models with different power-performance operating points. The proposed architecture and circuits are evaluated with SPICE simulation in a 65 nm CMOS technology. The simulation results indicate that the proposed heterogeneous architecture improves the energy efficiency to 2.04 TOPS/W, while the conventional monolithic and single voltage domain architecture exhibits an energy efficiency of 0.0458 TOPS/W. In addition, the total power consumption of the accelerator SoC is reduced to 1.34 W as compared to the 3.72 W consumed by the baseline architecture when all multiply-and-accumulate (MACs) units operate at a voltage of 0.45 V.
Among the many path planning algorithms, the RRT* algorithm and the Informed RRT* algorithm are the most popular. Both of them can complete the single path planning effectively. However, because the planning effect of...
详细信息
暂无评论