Deep learning has achieved good results in the field of image recognition due to the key role of the optimizer in a deep learning network. In this work, the optimizers of dynamical system models are established,and th...
详细信息
Deep learning has achieved good results in the field of image recognition due to the key role of the optimizer in a deep learning network. In this work, the optimizers of dynamical system models are established,and the influence of parameter adjustments on the dynamic performance of the system is proposed. This is a useful supplement to the theoretical control models of optimizers. First, the system control model is derived based on the iterative formula of the optimizer, the optimizer model is expressed by differential equations, and the control equation of the optimizer is established. Second, based on the system control model of the optimizer, the phase trajectory process of the optimizer model and the influence of different hyperparameters on the system performance of the learning model are analyzed. Finally, controllers with different optimizers and different hyperparameters are used to classify the MNIST and CIFAR-10 datasets to verify the effects of different optimizers on the model learning performance and compare them with related methods. Experimental results show that selecting appropriate optimizers can accelerate the convergence speed of the model and improve the accuracy of model recognition. Furthermore, the convergence speed and performance of the stochastic gradient descent(SGD) optimizer are better than those of the stochastic gradient descent-momentum(SGD-M) and Nesterov accelerated gradient(NAG) optimizers.
The prediction of processor performance has important referencesignificance for future processors. Both the accuracy and rationality of theprediction results are required. The hierarchical belief rule base (HBRB)can i...
详细信息
The prediction of processor performance has important referencesignificance for future processors. Both the accuracy and rationality of theprediction results are required. The hierarchical belief rule base (HBRB)can initially provide a solution to low prediction accuracy. However, theinterpretability of the model and the traceability of the results still warrantfurther investigation. Therefore, a processor performance prediction methodbased on interpretable hierarchical belief rule base (HBRB-I) and globalsensitivity analysis (GSA) is proposed. The method can yield more reliableprediction results. Evidence reasoning (ER) is firstly used to evaluate thehistorical data of the processor, followed by a performance prediction modelwith interpretability constraints that is constructed based on HBRB-I. Then,the whale optimization algorithm (WOA) is used to optimize the ***, to test the interpretability of the performance predictionprocess, GSA is used to analyze the relationship between the input and thepredicted output indicators. Finally, based on the UCI database processordataset, the effectiveness and superiority of the method are verified. Accordingto our experiments, our prediction method generates more reliable andaccurate estimations than traditional models.
Cancer remains a leading cause of mortality worldwide, with early detection and accurate diagnosis critical to improving patient outcomes. While computer-aided diagnosis systems powered by deep learning have shown con...
详细信息
Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell computers and Humans Apart)has become a key method to distinguish humans from *** text-...
详细信息
Enhancing website security is crucial to combat malicious activities,and CAPTCHA(Completely Automated Public Turing tests to tell computers and Humans Apart)has become a key method to distinguish humans from *** text-based CAPTCHAs are designed to challenge machines while remaining human-readable,recent advances in deep learning have enabled models to recognize them with remarkable *** this regard,we propose a novel two-layer visual attention framework for CAPTCHA recognition that builds on traditional attention mechanisms by incorporating Guided Visual Attention(GVA),which sharpens focus on relevant visual *** have specifically adapted the well-established image captioning task to address this *** approach utilizes the first-level attention module as guidance to the second-level attention component,incorporating two LSTM(Long Short-Term Memory)layers to enhance CAPTCHA *** extensive evaluation across four diverse datasets—Weibo,BoC(Bank of China),Gregwar,and Captcha 0.3—shows the adaptability and efficacy of our *** approach demonstrated impressive performance,achieving an accuracy of 96.70%for BoC and 95.92%for *** results underscore the effectiveness of our method in accurately recognizing and processing CAPTCHA datasets,showcasing its robustness,reliability,and ability to handle varied challenges in CAPTCHA recognition.
Video colorization aims to add color to grayscale or monochrome *** existing methods have achieved substantial and noteworthy results in the field of image colorization,video colorization presents more formidable obst...
详细信息
Video colorization aims to add color to grayscale or monochrome *** existing methods have achieved substantial and noteworthy results in the field of image colorization,video colorization presents more formidable obstacles due to the additional necessity for temporal ***,there is rarely a systematic review of video colorization *** this paper,we aim to review existing state-of-the-art video colorization *** addition,maintaining spatial-temporal consistency is pivotal to the process of video *** gain deeper insight into the evolution of existing methods in terms of spatial-temporal consistency,we further review video colorization methods from a novel *** colorization methods can be categorized into four main categories:optical-flow based methods,scribble-based methods,exemplar-based methods,and fully automatic ***,optical-flow based methods rely heavily on accurate optical-flow estimation,scribble-based methods require extensive user interaction and modifications,exemplar-based methods face challenges in obtaining suitable reference images,and fully automatic methods often struggle to meet specific colorization *** also discuss the existing challenges and highlight several future research opportunities worth exploring.
With the escalation of global warming and human activities, large-scale wildfires have become increasingly frequent, posing significant threats to both ecological environments and human societal safety. Satellite remo...
详细信息
Real-time systems are widely implemented in the Internet of Things(IoT) and safety-critical systems, both of which have generated enormous social value. Aiming at the classic schedulability analysis problem in real-ti...
详细信息
Real-time systems are widely implemented in the Internet of Things(IoT) and safety-critical systems, both of which have generated enormous social value. Aiming at the classic schedulability analysis problem in real-time systems, we proposed an exact Boolean analysis based on interference(EBAI) for schedulability analysis in real-time systems. EBAI is based on worst-case interference time(WCIT), which considers both the release jitter and blocking time of the task. We improved the efficiency of the three existing tests and provided a comprehensive summary of related research results in the field. Abundant experiments were conducted to compare EBAI with other related results. Our evaluation showed that in certain cases, the runtime gain achieved using our analysis method may exceed 73% compared to the stateof-the-art schedulability test. Furthermore, the benefits obtained from our tests grew with the number of tasks, reaching a level suitable for practical application. EBAI is oriented to the five-tuple real-time task model with stronger expression ability and possesses a low runtime overhead. These characteristics make it applicable in various real-time systems such as spacecraft, autonomous vehicles, industrial robots, and traffic command systems.
A solid solution 6063 aluminium alloy features an exceptional combination of strength and ductility at 77 ***,the deformation mechanisms responsible for superior strength-ductility synergy and excellent strain hardeni...
详细信息
A solid solution 6063 aluminium alloy features an exceptional combination of strength and ductility at 77 ***,the deformation mechanisms responsible for superior strength-ductility synergy and excellent strain hardening capacity at a cryogenic temperature of the alloy were comparatively investigated by in-situ electron backscatter diffraction(EBSD)observations coupled with transmission electron microscopy(TEM)characterization and fracture morphologies at both 298 and 77 *** is found that kernel average misorientation(KAM)mappings and quantified KAM in degree suggest a higher proportion of geometri-cally necessary dislocations(GNDs)at 77 *** existence of orientation scatter partitions at 77 K implies the activation of multiple slip systems,which is consistent with the results of potential slip systems cal-culated by Taylor ***,dislocation tangles characterized by brief and curved dislocation cells and abundant small dimples have been observed at 77 *** temperature-mediated activation of dislo-cations facilitates the increased dislocations,thus enhancing the strain hardening capacity and ductility of the *** research enriches cryogenic deformation theory and provides valuable insights into the design of high-performance aluminium alloys that are suitable for cryogenic applications.
High-temperature energy storage performance of dielectric capacitors is cru-cial for the next generation of power electronic ***,conduction losses rise sharply at elevated temperature,limiting the application of energ...
详细信息
High-temperature energy storage performance of dielectric capacitors is cru-cial for the next generation of power electronic ***,conduction losses rise sharply at elevated temperature,limiting the application of energy storage ***,the mica films magnetron sputtered by different insulating layers are specifically investigated,which exhibit the excellent high-temperature energy storage *** experimental results revealed that the PbZrO3/Al2O3/PbZrO3(PZO/AO/PZO)interface insulating layers can effec-tively reduce the high-temperature leakage current and conduction loss of the composite ***,the ultrahigh energy storage density(Wrec)and charge‒discharge efficiency(η)can be achieved simultaneously in the flexi-ble mica-based composite ***,PZO/AO/PZO/mica/PZO/AO/PZO(PAPMPAP)films possess excellent Wrec of 27.5 J/cm3 andηof 87.8%at 200◦C,which are significantly better than currently reported high-temperature capaci-tive energy storage dielectric *** with outstanding power density and electrical cycling stability,the flexible films in this work have great appli-cation potential in high-temperature energy storage ***,the magnetron sputtering technology can deposit large-area nanoscale insulating layers on the surface of capacitor films,which can provide technical support for the industrial production of capacitors.
The behavior of users on online life service platforms like Meituan and Yelp often occurs within specific finegrained spatiotemporal contexts(i.e., when and where). Recommender systems, designed to serve millions of u...
详细信息
The behavior of users on online life service platforms like Meituan and Yelp often occurs within specific finegrained spatiotemporal contexts(i.e., when and where). Recommender systems, designed to serve millions of users, typically operate in a fully server-based manner, requiring on-device users to upload their behavioral data, including fine-grained spatiotemporal contexts, to the server, which has sparked public concern regarding privacy. Consequently, user devices only upload coarse-grained spatiotemporal contexts for user privacy protection. However, previous research mostly focuses on modeling fine-grained spatiotemporal contexts using knowledge graph convolutional models, which are not applicable to coarse-grained spatiotemporal contexts in privacy-constrained recommender systems. In this paper, we investigate privacy-preserving recommendation by leveraging coarse-grained spatiotemporal contexts. We propose the coarse-grained spatiotemporal knowledge graph for privacy-preserving recommendation(CSKG), which explicitly models spatiotemporal co-occurrences using common-sense knowledge from coarse-grained contexts. Specifically, we begin by constructing a spatiotemporal knowledge graph tailored to coarse-grained spatiotemporal contexts. Then we employ a learnable metagraph network that integrates common-sense information to filter and extract co-occurrences. CSKG evaluates the impact of coarsegrained spatiotemporal contexts on user behavior through the use of a knowledge graph convolutional network. Finally, we introduce joint learning to effectively learn representations. By conducting experiments on two real large-scale datasets,we achieve an average improvement of about 11.0% on two ranking metrics. The results clearly demonstrate that CSKG outperforms state-of-the-art baselines.
暂无评论