Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems.At the same time,the computational complexity and resource consumption of t...Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems.At the same time,the computational complexity and resource consumption of these networks continue to increase.This poses a significant challenge to the deployment of such networks,especially in real-time applications or on resource-limited devices.Thus,network acceleration has become a hot topic within the deep learning community.As for hardware implementation of deep neural networks,a batch of accelerators based on a field-programmable gate array(FPGA) or an application-specific integrated circuit(ASIC)have been proposed in recent years.In this paper,we provide a comprehensive survey of recent advances in network acceleration,compression,and accelerator design from both algorithm and hardware points of view.Specifically,we provide a thorough analysis of each of the following topics:network pruning,low-rank approximation,network quantization,teacher–student networks,compact network design,and hardware accelerators.Finally,we introduce and discuss a few possible future directions.展开更多
Bio-inspired intelligence is in the spotlight in the field of international artificial intelligence,and unmanned combat aerial vehicle(UCAV),owing to its potential to perform dangerous,repetitive tasks in remote and h...Bio-inspired intelligence is in the spotlight in the field of international artificial intelligence,and unmanned combat aerial vehicle(UCAV),owing to its potential to perform dangerous,repetitive tasks in remote and hazardous,is very promising for the technological leadership of the nation and essential for improving the security of society.On the basis of introduction of bioinspired intelligence and UCAV,a series of new development thoughts on UCAV control are proposed,including artificial brain based high-level autonomous control for UCAV,swarm intelligence based cooperative control for multiple UCAVs,hy-brid swarm intelligence and Bayesian network based situation assessment under complicated combating environments, bio-inspired hardware based high-level autonomous control for UCAV,and meta-heuristic intelligence based heterogeneous cooperative control for multiple UCAVs and unmanned combat ground vehicles(UCGVs).The exact realization of the proposed new development thoughts can enhance the effectiveness of combat,while provide a series of novel breakthroughs for the intelligence,integration and advancement of future UCAV systems.展开更多
This paper presents a framework of a multi-terminal HVDC transmission system and its multi-functional control strategy.The framework possesses the basic characteristics of the DC-grid and is suitable in integrating di...This paper presents a framework of a multi-terminal HVDC transmission system and its multi-functional control strategy.The framework possesses the basic characteristics of the DC-grid and is suitable in integrating distributed power sources.The paper proposes the first architecture for a multiterminal HVDC transmission system using the VSC technology.Its control strategy offers various functionalities that include controls for operation mode,start-up and shutdown,DC voltage,and station online re-connecting,which are significantly different from the control of point-to-point VSC-HVDC systems.The framework has not only been evaluated in real-time simulation studies,but has also been implemented onsite for the first time via the China Southern Grid's Nan'ao Multi-terminal VSCHVDC(VSC-MTDC)project.This paper gives a brief review of the current research and engineering achievements in this field,which includes four aspects:the architecture of the VSCMTDC system,the structure of the control and protection system,simulation verification tests setting,and the results of real-time hardware in hardware in loop(HIL)simulation studies and onsite tests.展开更多
文摘Deep neural networks have evolved remarkably over the past few years and they are currently the fundamental tools of many intelligent systems.At the same time,the computational complexity and resource consumption of these networks continue to increase.This poses a significant challenge to the deployment of such networks,especially in real-time applications or on resource-limited devices.Thus,network acceleration has become a hot topic within the deep learning community.As for hardware implementation of deep neural networks,a batch of accelerators based on a field-programmable gate array(FPGA) or an application-specific integrated circuit(ASIC)have been proposed in recent years.In this paper,we provide a comprehensive survey of recent advances in network acceleration,compression,and accelerator design from both algorithm and hardware points of view.Specifically,we provide a thorough analysis of each of the following topics:network pruning,low-rank approximation,network quantization,teacher–student networks,compact network design,and hardware accelerators.Finally,we introduce and discuss a few possible future directions.
基金supported by the National Natural Science Foundation of China(Grant Nos.60975072,60604009)the Aeronautical Science Foundation of China(Grant No.2008ZC01006)+2 种基金Beijing NOVA Program Foundation(Grant No.2007A017)the Fundamental Research Funds for the Central Universities(Grant No.YWF-10-01-A18)the Program for New Century Excellent Talents in University of China(Grant No.NCET-10-0021)
文摘Bio-inspired intelligence is in the spotlight in the field of international artificial intelligence,and unmanned combat aerial vehicle(UCAV),owing to its potential to perform dangerous,repetitive tasks in remote and hazardous,is very promising for the technological leadership of the nation and essential for improving the security of society.On the basis of introduction of bioinspired intelligence and UCAV,a series of new development thoughts on UCAV control are proposed,including artificial brain based high-level autonomous control for UCAV,swarm intelligence based cooperative control for multiple UCAVs,hy-brid swarm intelligence and Bayesian network based situation assessment under complicated combating environments, bio-inspired hardware based high-level autonomous control for UCAV,and meta-heuristic intelligence based heterogeneous cooperative control for multiple UCAVs and unmanned combat ground vehicles(UCGVs).The exact realization of the proposed new development thoughts can enhance the effectiveness of combat,while provide a series of novel breakthroughs for the intelligence,integration and advancement of future UCAV systems.
基金supported by the 863 National High Technology Research and Development Program of China(2011AA05AI02)China Southern Power Grid Company.
文摘This paper presents a framework of a multi-terminal HVDC transmission system and its multi-functional control strategy.The framework possesses the basic characteristics of the DC-grid and is suitable in integrating distributed power sources.The paper proposes the first architecture for a multiterminal HVDC transmission system using the VSC technology.Its control strategy offers various functionalities that include controls for operation mode,start-up and shutdown,DC voltage,and station online re-connecting,which are significantly different from the control of point-to-point VSC-HVDC systems.The framework has not only been evaluated in real-time simulation studies,but has also been implemented onsite for the first time via the China Southern Grid's Nan'ao Multi-terminal VSCHVDC(VSC-MTDC)project.This paper gives a brief review of the current research and engineering achievements in this field,which includes four aspects:the architecture of the VSCMTDC system,the structure of the control and protection system,simulation verification tests setting,and the results of real-time hardware in hardware in loop(HIL)simulation studies and onsite tests.
