The integration of Mixed Reality(MR)technology into Autonomous Vehicles(AVs)has ushered in a new era for the automotive industry,offering heightened safety,convenience,and passenger ***,the substantial and varied data...
详细信息
The integration of Mixed Reality(MR)technology into Autonomous Vehicles(AVs)has ushered in a new era for the automotive industry,offering heightened safety,convenience,and passenger ***,the substantial and varied data generated by MR-Connected AVs(MR-CAVs),encompassing both highly dynamic and static information,presents formidable challenges for efficient data management and *** this paper,we formulate our indexing problem as a constrained optimization problem,with the aim of maximizing the utility function that represents the overall performance of our indexing *** optimization problem encompasses multiple decision variables and constraints,rendering it mathematically infeasible to solve ***,we propose a heuristic algorithm to address the combinatorial complexity of the *** heuristic indexing algorithm efficiently divides data into highly dynamic and static categories,distributing the index across Roadside Units(RSUs)and optimizing query *** approach takes advantage of the computational capabilities of edge servers or RSUs to perform indexing operations,thereby shifting the burden away from the vehicles *** algorithm strategically places data in the cache,optimizing cache hit rate and space utilization while reducing *** quantitative evaluation demonstrates the superiority of our proposed scheme,with significant reductions in latency(averaging 27%-49.25%),a 30.75%improvement in throughput,a 22.50%enhancement in cache hit rate,and a 32%-50.75%improvement in space utilization compared to baseline schemes.
Known learning rules tend to fall near one of two extremes: single-pass associative learning with low complexity and capacity, and multi-pass iterative learning with high complexity and capacity. In this work we inves...
详细信息
Known learning rules tend to fall near one of two extremes: single-pass associative learning with low complexity and capacity, and multi-pass iterative learning with high complexity and capacity. In this work we investigate the mathematical feasibility of learning rules that are both single-pass and achieve the theoretical upper bound on capacity. We consider a fairly broad family of learning rules we call "span rules," which include known rules such as Hebbian learning, perceptron learning, and backpropagation as special cases. To our knowledge, previous work has not determined whether single-pass, full-capacity span rules exist, even in the most fundamental case of a linear threshold neuron with binary input vectors, which is the focus of this study. We derive a necessary condition for the existence of such learning rules, which takes the form of a linear program, and show that the linear program is infeasible. This establishes an impossibility result that span rules can not be both single-pass and full-capacity. Copyright 2024 by the author(s)
Modern technological advancements have made social media an essential component of daily *** media allow individuals to share thoughts,emotions,and *** analysis plays the function of evaluating whether the sentiment o...
详细信息
Modern technological advancements have made social media an essential component of daily *** media allow individuals to share thoughts,emotions,and *** analysis plays the function of evaluating whether the sentiment of the text is positive,negative,neutral,or any other personal emotion to understand the sentiment context of the *** analysis is essential in business and society because it impacts strategic *** analysis involves challenges due to lexical variation,an unlabeled dataset,and text distance *** execution time increases due to the sequential processing of the sequence ***,the calculation times for the Transformer models are reduced because of the parallel *** study uses a hybrid deep learning strategy to combine the strengths of the Transformer and Sequence models while ignoring their *** particular,the proposed model integrates the Decoding-enhanced with Bidirectional Encoder Representations from Transformers(BERT)attention(DeBERTa)and the Gated Recurrent Unit(GRU)for sentiment *** the Decoding-enhanced BERT technique,the words are mapped into a compact,semantic word embedding space,and the Gated Recurrent Unit model can capture the distance contextual semantics *** proposed hybrid model achieves F1-scores of 97%on the Twitter Large Language Model(LLM)dataset,which is much higher than the performance of new techniques.
Recent studies introduce new controllers that leverage the flexibility of inverter-interfaced generation for voltage control. However, only a few discuss the practical implementations of such controllers. Bridging thi...
详细信息
— The direct pulsewidth modulation (PWM) ac–ac converters are seeing rapid development due to their single-stage power conversion with reduced footprints, due to the elimination of intermediate dc-link capacitor. Ho...
详细信息
Ensuring grid stability with increasing penetration of inverter-based resources requires robust Grid Forming (GFM) control methods. Droop control is a prevalent method, but its reliance on low-pass filters (LPF) for p...
详细信息
There is an immediate threat to the highway transportation system from road accidents, which can cause death, serious injury, and property damage. Accidents involving motor vehicles cause significant injury or death t...
详细信息
We study deep neural networks for the multi-label classification (M-lab) task through the lens of neural collapse (NC). Previous works have been restricted to the multi-class classification setting and discovered a pr...
详细信息
We study deep neural networks for the multi-label classification (M-lab) task through the lens of neural collapse (NC). Previous works have been restricted to the multi-class classification setting and discovered a prevalent NC phenomenon comprising of the following properties for the last-layer features: (i) the variability of features within every class collapses to zero, (ii) the set of feature means form an equi-angular tight frame (ETF), and (iii) the last layer classifiers collapse to the feature mean upon some scaling. We generalize the study to multi-label learning, and prove for the first time that a generalized NC phenomenon holds with the "pick-all-label" formulation, which we term as M-lab NC. While the ETF geometry remains consistent for features with a single label, multi-label scenarios introduce a unique combinatorial aspect we term the"tag-wise average" property, where the means of features with multiple labels are the scaled averages of means for single-label instances. Theoretically, under proper assumptions on the features, we establish that the only global optimizer of the pick-all-label cross-entropy loss satisfy the multi-label NC. In practice, we demonstrate that our findings can lead to better test performance with more efficient training techniques for M-lab learning. Copyright 2024 by the author(s)
Microservices architecture is popular due to its scalability and flexibility. However, managing and troubleshooting distributed microservices-based systems can be challenging and time consuming. Auto-remediation of an...
详细信息
Ultradense low-Earth orbit (LEO) satellite-terrestrial network (ULSN) has evolved as a new paradigm to provide ubiquitous and high-capacity communications in next generation wireless networks. However, the direct LEO ...
详细信息
暂无评论