Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall&quo...Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall",limiting the data transfer between memory and processing units[1,2].Compute-in-memory(CIM)technologies,particularly analogue CIM with memristor crossbars,are promising because of their high energy efficiency,computational parallelism,and integration density for NN computations[3].In practical applications,analogue CIM excels in tasks like speech recognition and image classification,revealing its unique advantages.For instance,it efficiently processes vast amounts of audio data in speech recognition,achieving high accuracy with minimal power consumption.In image classification,the high parallelism of analogue CIM significantly speeds up feature extraction and reduces processing time.With the boosting development of AI applications,the demands for computational accuracy and task complexity are rising continually.However,analogue CIM systems are limited in handling complex regression tasks with needs of precise floating-point(FP)calculations.They are primarily suited for the classification tasks with low data precision and a limited dynamic range[4].展开更多
Unmanned Aerial Vehicles(UAVs)coupled with deep learning such as Convolutional Neural Networks(CNNs)have been widely applied across numerous domains,including agriculture,smart city monitoring,and fire rescue operatio...Unmanned Aerial Vehicles(UAVs)coupled with deep learning such as Convolutional Neural Networks(CNNs)have been widely applied across numerous domains,including agriculture,smart city monitoring,and fire rescue operations,owing to their malleability and versatility.However,the computation-intensive and latency-sensitive natures of CNNs present a formidable obstacle to their deployment on resource-constrained UAVs.Some early studies have explored a hybrid approach that dynamically switches between lightweight and complex models to balance accuracy and latency.However,they often overlook scenarios involving multiple concurrent CNN streams,where competition for resources between streams can substantially impact latency and overall system performance.In this paper,we first investigate the deployment of both lightweight and complex models for multiple CNN streams in UAV swarm.Specifically,we formulate an optimization problem to minimize the total latency across multiple CNN streams,under the constraints on UAV memory and the accuracy requirement of each stream.To address this problem,we propose an algorithm called Adaptive Model Switching of collaborative inference for MultiCNN streams(AMSM)to identify the inference strategy with a low latency.Simulation results demonstrate that the proposed AMSM algorithm consistently achieves the lowest latency while meeting the accuracy requirements compared to benchmark algorithms.展开更多
COMPUTATIONAL experiments method is an essential tool for analyzing,designing,managing,and integrating complex systems.However,a significant challenge arises in constructing agents with human-like characteristics to f...COMPUTATIONAL experiments method is an essential tool for analyzing,designing,managing,and integrating complex systems.However,a significant challenge arises in constructing agents with human-like characteristics to form an AI society.Agent modeling typically encompasses four levels:1)The autonomy features of agents,e.g.,perception,behavior,and decision-making;2)The evolutionary features of agents,e.g.,bounded rationality,heterogeneity,and learning evolution;3)The social features of agents,e.g.,interaction,cooperation,and competition;4)The emergent features of agents,e.g.,gaming with environments or regulatory strategies.Traditional modeling techniques primarily derive from ABMs(Agent-based Models)and incorporate various emerging technologies(e.g.,machine learning,big data,and social networks),which can enhance modeling capabilities,while amplifying the complexity[1].展开更多
A class of new fuzzy inference systems New-FISs is presented.Compared with the standard fuzzy system, New-FIS is still a universal approximator and has no fuzzy rule base and linearly parameter growth. Thus, it effect...A class of new fuzzy inference systems New-FISs is presented.Compared with the standard fuzzy system, New-FIS is still a universal approximator and has no fuzzy rule base and linearly parameter growth. Thus, it effectively overcomes the second "curse of dimensionality":there is an exponential growth in the number of parameters of a fuzzy system as the number of input variables,resulting in surprisingly reduced computational complexity and being especially suitable for applications,where the complexity is of the first importance with respect to the approximation accuracy.展开更多
Given the fast growth of intelligent devices, it is expected that a large number of high-stakes artificial intelligence (AI) applications, e. g., drones, autonomous cars, and tac?tile robots, will be deployed at the e...Given the fast growth of intelligent devices, it is expected that a large number of high-stakes artificial intelligence (AI) applications, e. g., drones, autonomous cars, and tac?tile robots, will be deployed at the edge of wireless networks in the near future. Therefore, the intelligent communication networks will be designed to leverage advanced wireless tech?niques and edge computing technologies to support AI-enabled applications at various end devices with limited communication, computation, hardware and energy resources. In this article, we present the principles of efficient deployment of model inference at network edge to provide low-latency and energy-efficient AI services. This includes the wireless distribut?ed computing framework for low-latency device distributed model inference as well as the wireless cooperative transmission strategy for energy-efficient edge cooperative model infer?ence. The communication efficiency of edge inference systems is further improved by build?ing up a smart radio propagation environment via intelligent reflecting surface.展开更多
In this paper, I shall sketch a new way to consider a Lindenbaum-Tarski algebra as a 3D logical space in which any one (of the 256 statements) occupies a well-defined position and it is identified by a numerical ID. T...In this paper, I shall sketch a new way to consider a Lindenbaum-Tarski algebra as a 3D logical space in which any one (of the 256 statements) occupies a well-defined position and it is identified by a numerical ID. This allows pure mechanical computation both for generating rules and inferences. It is shown that this abstract formalism can be geometrically represented with logical spaces and subspaces allowing a vectorial representation. Finally, it shows the application to quantum computing through the example of three coupled harmonic oscillators.展开更多
Hyperparameter tuning is a key step in developing high-performing machine learning models, but searching large hyperparameter spaces requires extensive computation using standard sequential methods. This work analyzes...Hyperparameter tuning is a key step in developing high-performing machine learning models, but searching large hyperparameter spaces requires extensive computation using standard sequential methods. This work analyzes the performance gains from parallel versus sequential hyperparameter optimization. Using scikit-learn’s Randomized SearchCV, this project tuned a Random Forest classifier for fake news detection via randomized grid search. Setting n_jobs to -1 enabled full parallelization across CPU cores. Results show the parallel implementation achieved over 5× faster CPU times and 3× faster total run times compared to sequential tuning. However, test accuracy slightly dropped from 99.26% sequentially to 99.15% with parallelism, indicating a trade-off between evaluation efficiency and model performance. Still, the significant computational gains allow more extensive hyperparameter exploration within reasonable timeframes, outweighing the small accuracy decrease. Further analysis could better quantify this trade-off across different models, tuning techniques, tasks, and hardware.展开更多
Optimizing the deployment of large language models(LLMs)in edge computing environments is critical for enhancing privacy and computational efficiency.In the path toward efficient wireless LLM inference in edge computi...Optimizing the deployment of large language models(LLMs)in edge computing environments is critical for enhancing privacy and computational efficiency.In the path toward efficient wireless LLM inference in edge computing,this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs.Accordingly,this study introduces a framework taking inspiration from model-based reinforcement learning to determine the optimal splitting point across the edge and user equipment.By incorporating a reward surrogate model,our approach significantly reduces the computational cost of frequent performance evaluations.Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions,providing a robust solution for LLM deployment in decentralized settings.展开更多
According to the requirement of computer forensic and network forensic, a novel forensic computing model is presented, which exploits XML/OEM/RM data model, Data fusion technology, forensic knowledgebase, inference me...According to the requirement of computer forensic and network forensic, a novel forensic computing model is presented, which exploits XML/OEM/RM data model, Data fusion technology, forensic knowledgebase, inference mechanism of expert system and evidence mining engine. This model takes advantage of flexility and openness, so it can be widely used in mining evidence.展开更多
Unmanned aerial vehicle(UAV)-enabled edge computing is emerging as a potential enabler for Artificial Intelligence of Things(AIoT)in the forthcoming sixth-generation(6G)communication networks.With the use of flexible ...Unmanned aerial vehicle(UAV)-enabled edge computing is emerging as a potential enabler for Artificial Intelligence of Things(AIoT)in the forthcoming sixth-generation(6G)communication networks.With the use of flexible UAVs,massive sensing data is gathered and processed promptly without considering geographical locations.Deep neural networks(DNNs)are becoming a driving force to extract valuable information from sensing data.However,the lightweight servers installed on UAVs are not able to meet the extremely high requirements of inference tasks due to the limited battery capacities of UAVs.In this work,we investigate a DNN model placement problem for AIoT applications,where the trained DNN models are selected and placed on UAVs to execute inference tasks locally.It is impractical to obtain future DNN model request profiles and system operation states in UAV-enabled edge computing.The Lyapunov optimization technique is leveraged for the proposed DNN model placement problem.Based on the observed system overview,an advanced online placement(AOP)algorithm is developed to solve the transformed problem in each time slot,which can reduce DNN model transmission delay and disk I/O energy cost simultaneously while keeping the input data queues stable.Finally,extensive simulations are provided to depict the effectiveness of the AOP algorithm.The numerical results demonstrate that the AOP algorithm can reduce 18.14%of the model placement cost and 29.89%of the input data queue backlog on average by comparing it with benchmark algorithms.展开更多
This article is a continuation of the work“Intelligent robust control of redundant smart robotic arm Pt I:Soft computing KB optimizer-deep machine learning IT”.In the first part of the paper,we examined control syst...This article is a continuation of the work“Intelligent robust control of redundant smart robotic arm Pt I:Soft computing KB optimizer-deep machine learning IT”.In the first part of the paper,we examined control systems with constant coefficients of the conventional PID controller(based on genetic algorithm)and intelligent control systems based on soft computing technologies.For demonstration,MatLab/Simulink models and a test benchmark of the robot manipulator demonstrated.Advantages and limitations of intelligent control systems based on soft computing technology discussed.Intelligent main element of the control system based on soft computing is a fuzzy controller with a knowledge base in it.In the first part of the article,two ways to implement fuzzy controllers showed.First way applyied one controller for all links of the manipulator and showed the best performance.However,such an implementation is not possible in complex control objects,such as a manipulator with seven degrees of freedom(7DOF).The second way use of separated control when an independent fuzzy controller controls each link.The control decomposition due to a slight decrease in the quality of management has greatly simplified the processes of creating and placing knowledge bases.In this Pt II,to eliminate the mismatch of the work of separate independent fuzzy controllers,methods for organizing coordination control based on quantum computing technologies to create robust intelligent control systems for robotic manipulators with 3DOF and 7DOF described.Quantum supremacy of developed end-to-end IT design of robust intelligent control systems demonstrated.展开更多
The task of an intelligent control system design applying soft and quantum computational intelligence technologies discussed.An example of a control object as a mobile robot with redundant robotic manipulator and ster...The task of an intelligent control system design applying soft and quantum computational intelligence technologies discussed.An example of a control object as a mobile robot with redundant robotic manipulator and stereovision introduced.Design of robust knowledge bases is performed using a developed computational intelligence-quantum/soft computing toolkit(QC/SCOptKBTM).The knowledge base self-organization process of fuzzy homogeneous regulators through the application of end-to-end IT of quantum computing described.The coordination control between the mobile robot and redundant manipulator with stereovision based on soft computing described.The general design methodology of a generalizing control unit based on the physical laws of quantum computing(quantum information-thermodynamic trade-off of control quality distribution and knowledge base self-organization goal)is considered.The modernization of the pattern recognition system based on stereo vision technology presented.The effectiveness of the proposed methodology is demonstrated in comparison with the structures of control systems based on soft computing for unforeseen control situations with sensor system.The main objective of this article is to demonstrate the advantages of the approach based on quantum/soft computing.展开更多
文摘Developing efficient neural network(NN)computing systems is crucial in the era of artificial intelligence(AI).Traditional von Neumann architectures have both the issues of"memory wall"and"power wall",limiting the data transfer between memory and processing units[1,2].Compute-in-memory(CIM)technologies,particularly analogue CIM with memristor crossbars,are promising because of their high energy efficiency,computational parallelism,and integration density for NN computations[3].In practical applications,analogue CIM excels in tasks like speech recognition and image classification,revealing its unique advantages.For instance,it efficiently processes vast amounts of audio data in speech recognition,achieving high accuracy with minimal power consumption.In image classification,the high parallelism of analogue CIM significantly speeds up feature extraction and reduces processing time.With the boosting development of AI applications,the demands for computational accuracy and task complexity are rising continually.However,analogue CIM systems are limited in handling complex regression tasks with needs of precise floating-point(FP)calculations.They are primarily suited for the classification tasks with low data precision and a limited dynamic range[4].
基金supported by the National Natural Science Foundation of China(No.61931011)the Jiangsu Provincial Key Research and Development Program,China(No.BE2021013-4)the Fundamental Research Project in University Characteristic Disciplines,China(No.ILF240071A24)。
文摘Unmanned Aerial Vehicles(UAVs)coupled with deep learning such as Convolutional Neural Networks(CNNs)have been widely applied across numerous domains,including agriculture,smart city monitoring,and fire rescue operations,owing to their malleability and versatility.However,the computation-intensive and latency-sensitive natures of CNNs present a formidable obstacle to their deployment on resource-constrained UAVs.Some early studies have explored a hybrid approach that dynamically switches between lightweight and complex models to balance accuracy and latency.However,they often overlook scenarios involving multiple concurrent CNN streams,where competition for resources between streams can substantially impact latency and overall system performance.In this paper,we first investigate the deployment of both lightweight and complex models for multiple CNN streams in UAV swarm.Specifically,we formulate an optimization problem to minimize the total latency across multiple CNN streams,under the constraints on UAV memory and the accuracy requirement of each stream.To address this problem,we propose an algorithm called Adaptive Model Switching of collaborative inference for MultiCNN streams(AMSM)to identify the inference strategy with a low latency.Simulation results demonstrate that the proposed AMSM algorithm consistently achieves the lowest latency while meeting the accuracy requirements compared to benchmark algorithms.
基金supported in part by National Key Research and Development Program of China(2021YFF0900800)National Natural Science Foundation of China(62472306,62441221,62206116)+2 种基金Tianjin University’s 2024 Special Project on Disciplinary Development(XKJS-2024-5-9)Tianjin University Talent Innovation Reward Program for Literature&Science Graduate Student(C1-2022-010)Shanxi Province Social Science Foundation(2020F002).
文摘COMPUTATIONAL experiments method is an essential tool for analyzing,designing,managing,and integrating complex systems.However,a significant challenge arises in constructing agents with human-like characteristics to form an AI society.Agent modeling typically encompasses four levels:1)The autonomy features of agents,e.g.,perception,behavior,and decision-making;2)The evolutionary features of agents,e.g.,bounded rationality,heterogeneity,and learning evolution;3)The social features of agents,e.g.,interaction,cooperation,and competition;4)The emergent features of agents,e.g.,gaming with environments or regulatory strategies.Traditional modeling techniques primarily derive from ABMs(Agent-based Models)and incorporate various emerging technologies(e.g.,machine learning,big data,and social networks),which can enhance modeling capabilities,while amplifying the complexity[1].
基金This work was supported by the RGC Competitive Earmarked Research Grant (No. PolyU 5065/98E)Natural Science Foundation of China (No. 60225015)+1 种基金Natural Science Foundation of Jiangsu Province (No. BK2003017)National Key Labruary of Novel Software Tech
文摘A class of new fuzzy inference systems New-FISs is presented.Compared with the standard fuzzy system, New-FIS is still a universal approximator and has no fuzzy rule base and linearly parameter growth. Thus, it effectively overcomes the second "curse of dimensionality":there is an exponential growth in the number of parameters of a fuzzy system as the number of input variables,resulting in surprisingly reduced computational complexity and being especially suitable for applications,where the complexity is of the first importance with respect to the approximation accuracy.
文摘Given the fast growth of intelligent devices, it is expected that a large number of high-stakes artificial intelligence (AI) applications, e. g., drones, autonomous cars, and tac?tile robots, will be deployed at the edge of wireless networks in the near future. Therefore, the intelligent communication networks will be designed to leverage advanced wireless tech?niques and edge computing technologies to support AI-enabled applications at various end devices with limited communication, computation, hardware and energy resources. In this article, we present the principles of efficient deployment of model inference at network edge to provide low-latency and energy-efficient AI services. This includes the wireless distribut?ed computing framework for low-latency device distributed model inference as well as the wireless cooperative transmission strategy for energy-efficient edge cooperative model infer?ence. The communication efficiency of edge inference systems is further improved by build?ing up a smart radio propagation environment via intelligent reflecting surface.
文摘In this paper, I shall sketch a new way to consider a Lindenbaum-Tarski algebra as a 3D logical space in which any one (of the 256 statements) occupies a well-defined position and it is identified by a numerical ID. This allows pure mechanical computation both for generating rules and inferences. It is shown that this abstract formalism can be geometrically represented with logical spaces and subspaces allowing a vectorial representation. Finally, it shows the application to quantum computing through the example of three coupled harmonic oscillators.
文摘Hyperparameter tuning is a key step in developing high-performing machine learning models, but searching large hyperparameter spaces requires extensive computation using standard sequential methods. This work analyzes the performance gains from parallel versus sequential hyperparameter optimization. Using scikit-learn’s Randomized SearchCV, this project tuned a Random Forest classifier for fake news detection via randomized grid search. Setting n_jobs to -1 enabled full parallelization across CPU cores. Results show the parallel implementation achieved over 5× faster CPU times and 3× faster total run times compared to sequential tuning. However, test accuracy slightly dropped from 99.26% sequentially to 99.15% with parallelism, indicating a trade-off between evaluation efficiency and model performance. Still, the significant computational gains allow more extensive hyperparameter exploration within reasonable timeframes, outweighing the small accuracy decrease. Further analysis could better quantify this trade-off across different models, tuning techniques, tasks, and hardware.
基金supported by the National Key Research and Development Program of China(No.2024YFE0200600)the National Natural Science Foundation of China(No.62071425)+3 种基金the Zhejiang Key Research and Development Plan,China(No.2022C01093)the Zhejiang Provincial Natural Science Foundation of China(No.LR23F010005)the National Key Laboratory of Wireless Communications Foundation,China(No.2023KP01601)the Big Data and Intelligent Computing Key Lab of CQUPT,China(No.BDIC-2023-B-001)。
文摘Optimizing the deployment of large language models(LLMs)in edge computing environments is critical for enhancing privacy and computational efficiency.In the path toward efficient wireless LLM inference in edge computing,this study comprehensively analyzes the impact of different splitting points in mainstream open-source LLMs.Accordingly,this study introduces a framework taking inspiration from model-based reinforcement learning to determine the optimal splitting point across the edge and user equipment.By incorporating a reward surrogate model,our approach significantly reduces the computational cost of frequent performance evaluations.Extensive simulations demonstrate that this method effectively balances inference performance and computational load under varying network conditions,providing a robust solution for LLM deployment in decentralized settings.
基金Supported by the Scientific and TechnologicalBureau of the Ministry of Public Security of P.R.China ,the Projectof the Network Supervising Bureau(2005yycxhbst117) the Project ofthe 15th Overall Plan of Education Department of Hubei Province(2004d349) the Project of the 15th Overall Plan of Social ScienceFund of Hubei Province([2005]073)
文摘According to the requirement of computer forensic and network forensic, a novel forensic computing model is presented, which exploits XML/OEM/RM data model, Data fusion technology, forensic knowledgebase, inference mechanism of expert system and evidence mining engine. This model takes advantage of flexility and openness, so it can be widely used in mining evidence.
基金supported by the National Science Foundation of China(Grant No.62202118)the Top-Technology Talent Project from Guizhou Education Department(Qianjiao Ji[2022]073)+1 种基金the Natural Science Foundation of Hebei Province(Grant No.F2022203045 and F2022203026)the Central Government Guided Local Science and Technology Development Fund Project(Grant No.226Z0701G).
文摘Unmanned aerial vehicle(UAV)-enabled edge computing is emerging as a potential enabler for Artificial Intelligence of Things(AIoT)in the forthcoming sixth-generation(6G)communication networks.With the use of flexible UAVs,massive sensing data is gathered and processed promptly without considering geographical locations.Deep neural networks(DNNs)are becoming a driving force to extract valuable information from sensing data.However,the lightweight servers installed on UAVs are not able to meet the extremely high requirements of inference tasks due to the limited battery capacities of UAVs.In this work,we investigate a DNN model placement problem for AIoT applications,where the trained DNN models are selected and placed on UAVs to execute inference tasks locally.It is impractical to obtain future DNN model request profiles and system operation states in UAV-enabled edge computing.The Lyapunov optimization technique is leveraged for the proposed DNN model placement problem.Based on the observed system overview,an advanced online placement(AOP)algorithm is developed to solve the transformed problem in each time slot,which can reduce DNN model transmission delay and disk I/O energy cost simultaneously while keeping the input data queues stable.Finally,extensive simulations are provided to depict the effectiveness of the AOP algorithm.The numerical results demonstrate that the AOP algorithm can reduce 18.14%of the model placement cost and 29.89%of the input data queue backlog on average by comparing it with benchmark algorithms.
文摘This article is a continuation of the work“Intelligent robust control of redundant smart robotic arm Pt I:Soft computing KB optimizer-deep machine learning IT”.In the first part of the paper,we examined control systems with constant coefficients of the conventional PID controller(based on genetic algorithm)and intelligent control systems based on soft computing technologies.For demonstration,MatLab/Simulink models and a test benchmark of the robot manipulator demonstrated.Advantages and limitations of intelligent control systems based on soft computing technology discussed.Intelligent main element of the control system based on soft computing is a fuzzy controller with a knowledge base in it.In the first part of the article,two ways to implement fuzzy controllers showed.First way applyied one controller for all links of the manipulator and showed the best performance.However,such an implementation is not possible in complex control objects,such as a manipulator with seven degrees of freedom(7DOF).The second way use of separated control when an independent fuzzy controller controls each link.The control decomposition due to a slight decrease in the quality of management has greatly simplified the processes of creating and placing knowledge bases.In this Pt II,to eliminate the mismatch of the work of separate independent fuzzy controllers,methods for organizing coordination control based on quantum computing technologies to create robust intelligent control systems for robotic manipulators with 3DOF and 7DOF described.Quantum supremacy of developed end-to-end IT design of robust intelligent control systems demonstrated.
文摘The task of an intelligent control system design applying soft and quantum computational intelligence technologies discussed.An example of a control object as a mobile robot with redundant robotic manipulator and stereovision introduced.Design of robust knowledge bases is performed using a developed computational intelligence-quantum/soft computing toolkit(QC/SCOptKBTM).The knowledge base self-organization process of fuzzy homogeneous regulators through the application of end-to-end IT of quantum computing described.The coordination control between the mobile robot and redundant manipulator with stereovision based on soft computing described.The general design methodology of a generalizing control unit based on the physical laws of quantum computing(quantum information-thermodynamic trade-off of control quality distribution and knowledge base self-organization goal)is considered.The modernization of the pattern recognition system based on stereo vision technology presented.The effectiveness of the proposed methodology is demonstrated in comparison with the structures of control systems based on soft computing for unforeseen control situations with sensor system.The main objective of this article is to demonstrate the advantages of the approach based on quantum/soft computing.
