The future Sixth-Generation (6G) wireless systems are expected to encounter emerging services with diverserequirements. In this paper, 6G network resource orchestration is optimized to support customized networkslicin...
详细信息
The future Sixth-Generation (6G) wireless systems are expected to encounter emerging services with diverserequirements. In this paper, 6G network resource orchestration is optimized to support customized networkslicing of services, and place network functions generated by heterogeneous devices into available *** is a combinatorial optimization problem that is solved by developing a Particle Swarm Optimization (PSO)based scheduling strategy with enhanced inertia weight, particle variation, and nonlinear learning factor, therebybalancing the local and global solutions and improving the convergence speed to globally near-optimal *** show that the method improves the convergence speed and the utilization of network resourcescompared with other variants of PSO.
This paper addresses the finite-time anti-synchronization issue for a type of delayed memristive neural networks. By designing a novel memoryless state-feedback controller, novel criteria on finite-time anti-synchroni...
详细信息
Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sha...
详细信息
Federated learning is a widely used distributed learning approach in recent years,however,despite model training from collecting data become to gathering parameters,privacy violations may occur when publishing and sharing models.A dynamic approach is pro-posed to add Gaussian noise more effectively and apply differential privacy to federal deep ***,it is abandoning the traditional way of equally distributing the privacy budget e and adjusting the privacy budget to accommodate gradient descent federation learning dynamically,where the parameters depend on computation derived to avoid the impact on the algorithm that hyperparameters are created *** also incorporates adaptive threshold cropping to control the sensitivity,and finally,moments accountant is used to counting the∈consumed on the privacy‐preserving,and learning is stopped only if the∈_(total)by clients setting is reached,this allows the privacy budget to be adequately explored for model *** experimental results on real datasets show that the method training has almost the same effect as the model learning of non‐privacy,which is significantly better than the differential privacy method used by TensorFlow.
Modern recommendation systems are widely used in modern data *** random and sparse embedding lookup operations are the main performance bottleneck for processing recommendation systems on traditional platforms as they...
详细信息
Modern recommendation systems are widely used in modern data *** random and sparse embedding lookup operations are the main performance bottleneck for processing recommendation systems on traditional platforms as they induce abundant data movements between computing units and ***-based processing-in-memory(PIM)can resolve this problem by processing embedding vectors where they are ***,the embedding table can easily exceed the capacity limit of a monolithic ReRAM-based PIM chip,which induces off-chip accesses that may offset the PIM ***,we deploy the decomposed model on-chip and leverage the high computing efficiency of ReRAM to compensate for the decompression performance *** this paper,we propose ARCHER,a ReRAM-based PIM architecture that implements fully yon-chip recommendations under resource ***,we make a full analysis of the computation pattern and access pattern on the decomposed *** on the computation pattern,we unify the operations of each layer of the decomposed model in multiply-and-accumulate *** on the access observation,we propose a hierarchical mapping schema and a specialized hardware design to maximize resource *** the unified computation and mapping strategy,we can coordinatethe inter-processing elements *** evaluation shows that ARCHER outperforms the state-of-the-art GPU-based DLRM system,the state-of-the-art near-memory processing recommendation system RecNMP,and the ReRAM-based recommendation accelerator REREC by 15.79×,2.21×,and 1.21× in terms of performance and 56.06×,6.45×,and 1.71× in terms of energy savings,respectively.
In applicable scenarios, data used for forecasting and decision-making is usually expected to exhibit characteristics like time stationarity and the Markov property, and etc. However, industrial applications often ski...
详细信息
Generalized Lyapunov matrix equations appear in the fields of controllability analysis and model reduction of bilinear systems, stability analysis and optimal stabilization of linear stochastic systems, etc. The autho...
详细信息
Traditional cultural heritage is facing many challenges such as data fragmentation, privacy leakage and knowledge loss, which need to be solved with the help of the current advanced new generation of information techn...
详细信息
Synthetic aperture radar (SAR) ship detection plays a significant role in ocean monitoring. However, the current SAR ship detection methods face limitations in detecting small and dense ships. To address these issues,...
详细信息
Partial label learning (PLL) is a particular problem setting within weakly supervised learning. In PLL, each sample corresponds to a candidate label set in which only one label is true. However, in some practical appl...
详细信息
Cyber security is dynamic as defenders often need to adapt their defense postures. The state-ofthe-art is that the adaptation of network defense is done manually(i.e., tedious and error-prone). The ideal solution is t...
详细信息
Cyber security is dynamic as defenders often need to adapt their defense postures. The state-ofthe-art is that the adaptation of network defense is done manually(i.e., tedious and error-prone). The ideal solution is to automate adaptive network defense, which is however a difficult problem. As a first step towards automation, we propose investigating how to attain semi-automated adaptive network defense(SAND). We propose an approach extending the architecture of software-defined networking, which is centered on providing defenders with the capability to program the generation and deployment of dynamic defense rules enforced by network defense tools. We present the design and implementation of SAND, as well as the evaluation of the prototype implementation. Experimental results show that SAND can achieve agile and effective dynamic adaptations of defense rules(less than 15 ms on average for each operation), while only incurring a small performance overhead.
暂无评论