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.
Foundation models(FMs) [1] have revolutionized software development and become the core components of large software systems. This paradigm shift, however, demands fundamental re-imagining of software engineering theo...
Foundation models(FMs) [1] have revolutionized software development and become the core components of large software systems. This paradigm shift, however, demands fundamental re-imagining of software engineering theories and methodologies [2]. Instead of replacing existing software modules implemented by symbolic logic, incorporating FMs' capabilities to build software systems requires entirely new modules that leverage the unique capabilities of ***, while FMs excel at handling uncertainty, recognizing patterns, and processing unstructured data, we need new engineering theories that support the paradigm shift from explicitly programming and maintaining user-defined symbolic logic to creating rich, expressive requirements that FMs can accurately perceive and implement.
Partial multi-label learning（PML） allows learning from rich-semantic objects with inaccurate annotations, where a set of candidate labels are assigned to each training example but only some of them are valid. Existi...
详细信息
Partial multi-label learning（PML） allows learning from rich-semantic objects with inaccurate annotations, where a set of candidate labels are assigned to each training example but only some of them are valid. Existing approaches rely on disambiguation to tackle the PML problem, which aims to correct noisy candidate labels by recovering the ground-truth labeling information ahead of prediction model induction. However, this dominant strategy might be suboptimal as it usually needs extra assumptions that cannot be fully satisfied in real-world scenarios. Instead of label correction, we investigate another strategy to tackle the PML problem, where the potential ambiguity in PML data is eliminated by correcting instance features in a label-specific manner. Accordingly, a simple yet effective approach named PASE, i.e., partial multi-label learning via label-specific feature corrections, is proposed. Under a meta-learning framework, PASElearns to exert label-specific feature corrections so that potential ambiguity specific to each class label can be eliminated and the desired prediction model can be induced on these corrected instance features with the provided candidate labels. Comprehensive experiments on a wide range of synthetic and real-world data sets validate the effectiveness of the proposed approach.
The streaming model has been a popular model in big data computation. Streaming kernelization algorithms can be regarded as data compression processes on streaming data. In this study, we give a general method for dev...
The streaming model has been a popular model in big data computation. Streaming kernelization algorithms can be regarded as data compression processes on streaming data. In this study, we give a general method for developing computational lower bounds for streaming kernelization algorithms that is applicable to a large class of computational problems. As an example, we use the method to prove computational lower bounds for the well-known problem d-Hi TTin GSET.
Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but th...
详细信息
Predicting RNA binding protein(RBP) binding sites on circular RNAs(circ RNAs) is a fundamental step to understand their interaction mechanism. Numerous computational methods are developed to solve this problem, but they cannot fully learn the features. Therefore, we propose circ-CNNED, a convolutional neural network(CNN)-based encoding and decoding framework. We first adopt two encoding methods to obtain two original matrices. We preprocess them using CNN before fusion. To capture the feature dependencies, we utilize temporal convolutional network(TCN) and CNN to construct encoding and decoding blocks, respectively. Then we introduce global expectation pooling to learn latent information and enhance the robustness of circ-CNNED. We perform circ-CNNED across 37 datasets to evaluate its effect. The comparison and ablation experiments demonstrate that our method is superior. In addition, motif enrichment analysis on four datasets helps us to explore the reason for performance improvement of circ-CNNED.
Unmanned and aerial systems as interactors among different system components for communications,have opened up great opportunities for truth data discovery in Mobile Crowd Sensing(MCS)which has not been properly solve...
详细信息
Unmanned and aerial systems as interactors among different system components for communications,have opened up great opportunities for truth data discovery in Mobile Crowd Sensing(MCS)which has not been properly solved in the *** this paper,an Unmanned Aerial Vehicles-supported Intelligent Truth Discovery(UAV-ITD)scheme is proposed to obtain truth data at low-cost communications for *** main innovations of the UAV-ITD scheme are as follows:(1)UAV-ITD scheme takes the first step in employing UAV joint Deep Matrix Factorization(DMF)to discover truth data based on the trust mechanism for an Information Elicitation Without Verification(IEWV)problem in MCS.(2)This paper introduces a truth data discovery scheme for the first time that only needs to collect a part of n data samples to infer the data of the entire network with high accuracy,which saves more communication costs than most previous data collection schemes,where they collect n or kn data ***,we conducted extensive experiments to evaluate the UAV-ITD *** results show that compared with previous schemes,our scheme can reduce estimated truth error by 52.25%–96.09%,increase the accuracy of workers’trust evaluation by 0.68–61.82 times,and save recruitment costs by 24.08%–54.15%in truth data discovery.
With the arrival of the 5G era,wireless communication technologies and services are rapidly exhausting the limited spectrum *** auctions came into being,which can effectively utilize spectrum *** of the complexity of ...
详细信息
With the arrival of the 5G era,wireless communication technologies and services are rapidly exhausting the limited spectrum *** auctions came into being,which can effectively utilize spectrum *** of the complexity of the electronic spectrum auction network environment,the security of spectrum auction can not be *** scholars focus on researching the security of the single-sided auctions,while ignoring the practical scenario of a secure double spectrum auction where participants are composed of multiple sellers and *** begin to design the secure double spectrum auction mechanisms,in which two semi-honest agents are introduced to finish the spectrum auction *** these two agents may collude with each other or be bribed by buyers and sellers,which may create security risks,therefore,a secure double spectrum auction is proposed in this *** traditional secure double spectrum auctions,the spectrum auction server with Software Guard Extensions(SGX)component is used in this paper,which is an Ethereum blockchain platform that performs spectrum auctions.A secure double spectrum protocol is also designed,using SGX technology and cryptographic tools such as Paillier cryptosystem,stealth address technology and one-time ring signatures to well protect the private information of spectrum *** addition,the smart contracts provided by the Ethereum blockchain platform are executed to assist offline verification,and to verify important spectrum auction information to ensure the fairness and impartiality of spectrum ***,security analysis and performance evaluation of our protocol are discussed.
Named in-network computing service (NICS) is a potential computing paradigm emerged recently. Benefitted from the characteristics of named addressing and routing, NICS can be flexibly deployed on NDN router side and p...
详细信息
With the rise of artificial intelligence and cloud computing, machine-learning-as-a-service platforms,such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks for cloud applications. These propriet...
详细信息
With the rise of artificial intelligence and cloud computing, machine-learning-as-a-service platforms,such as Google, Amazon, and IBM, have emerged to provide sophisticated tasks for cloud applications. These proprietary models are vulnerable to model extraction attacks due to their commercial value. In this paper, we propose a time-efficient model extraction attack framework called Swift Theft that aims to steal the functionality of cloud-based deep neural network models. We distinguish Swift Theft from the existing works with a novel distribution estimation algorithm and reference model settings, finding the most informative query samples without querying the victim model. The selected query samples can be applied to various cloud models with a one-time selection. We evaluate our proposed method through extensive experiments on three victim models and six datasets, with up to 16 models for each dataset. Compared to the existing attacks, Swift Theft increases agreement(i.e., similarity) by 8% while consuming 98% less selecting time.
In the wake of rapid advancements in artificial intelligence(AI), we stand on the brink of a transformative leap in data systems. The imminent fusion of AI and DB(AI×DB) promises a new generation of data systems,...
详细信息
In the wake of rapid advancements in artificial intelligence(AI), we stand on the brink of a transformative leap in data systems. The imminent fusion of AI and DB(AI×DB) promises a new generation of data systems, which will relieve the burden on end-users across all industry sectors by featuring AI-enhanced functionalities, such as personalized and automated in-database AI-powered analytics, and selfdriving capabilities for improved system performance. In this paper, we explore the evolution of data systems with a focus on deepening the fusion of AI and DB. We present NeurDB, an AI-powered autonomous data system designed to fully embrace AI design in each major system component and provide in-database AI-powered analytics. We outline the conceptual and architectural overview of NeurDB, discuss its design choices and key components, and report its current development and future plan.
暂无评论