Under certain circumstances, E-learning can prevent students from interrupting their educational process about what happened during the lockdown, which caused education facilities from different levels to close. As a ...
详细信息
The standard power-law filter functions of order less than one, as well as their inverse counterparts, are implemented using only one active element in this work. The corresponding transfer functions are realized as i...
详细信息
Neural network pruning is a popular approach to reducing the computational complexity of deep neural *** recent years,as growing evidence shows that conventional network pruning methods employ inappropriate proxy metr...
详细信息
Neural network pruning is a popular approach to reducing the computational complexity of deep neural *** recent years,as growing evidence shows that conventional network pruning methods employ inappropriate proxy metrics,and as new types of hardware become increasingly available,hardware-aware network pruning that incorporates hardware characteristics in the loop of network pruning has gained growing attention,Both network accuracy and hardware efficiency(latency,memory consumption,etc.)are critical objectives to the success of network pruning,but the conflict between the multiple objectives makes it impossible to find a single optimal *** studies mostly convert the hardware-aware network pruning to optimization problems with a single *** this paper,we propose to solve the hardware-aware network pruning problem with Multi-Objective Evolutionary Algorithms(MOEAs).Specifically,we formulate the problem as a multi-objective optimization problem,and propose a novel memetic MOEA,namely HAMP,that combines an efficient portfoliobased selection and a surrogate-assisted local search,to solve *** studies demonstrate the potential of MOEAs in providing simultaneously a set of alternative solutions and the superiority of HAMP compared to the state-of-the-art hardware-aware network pruning method.
Cross-Domain Recommendation(CDR)aims to solve data sparsity and cold-start problems by utilizing a relatively information-rich source domain to improve the recommendation performance of the data-sparse target ***,most...
详细信息
Cross-Domain Recommendation(CDR)aims to solve data sparsity and cold-start problems by utilizing a relatively information-rich source domain to improve the recommendation performance of the data-sparse target ***,most existing approaches rely on the assumption of centralized storage of user data,which undoubtedly poses a significant risk of user privacy leakage because user data are highly *** this end,we propose a privacy-preserving Federated framework for Cross-Domain Recommendation,called *** our method,to avoid leakage of user privacy,a general recommendation model is trained on each user's personal device to obtain embeddings of users and items,and each client uploads weights to the central *** central server then aggregates the weights and distributes them to each client for ***,because the weights implicitly contain private information about the user,local differential privacy is adopted for the gradients before uploading them to the server for better protection of user *** distill the relationship of user embedding between two domains,an embedding transformation mechanism is used on the server side to learn the cross-domain embedding transformation *** experiments on real-world datasets demonstrate that ourmethod achieves performance comparable with that of existing data-centralized methods and effectively protects user privacy.
Network traffic classification is important for network security and management. State-of-the-art classifiers use deep learning techniques to automatically extract feature vectors from the traffic, which however lose ...
详细信息
Multimodal Emotion Recognition in Conversations (MERC) is an important topic in human-computer interaction. In the MERC task, conversations exhibit dynamic emotional dependency, including inter-speaker and intra-speak...
详细信息
Deep learning (DL) introduces a novel data-driven programming paradigm, where the system logic is constructed through data training. However, this approach poses challenges in terms of system analysis and defect detec...
详细信息
ISBN:
(纸本)9788995004395
Deep learning (DL) introduces a novel data-driven programming paradigm, where the system logic is constructed through data training. However, this approach poses challenges in terms of system analysis and defect detection. To address this issue, recent efforts have focused on testing deep learning systems using intuitive criteria known as Neuron Coverage (NC) and its variants. These criteria measure the activation proportion of neurons in a neural network. Unfortunately, recent DL applications have largely overlooked the importance of context during testing. To address this gap, this paper first incorporates the context of the DL pipeline deployed before test execution, such as medical diagnosis and Android Malware detection. Next, we formulate structural coverage criteria to guide test suite generation based on the properties of DL pipeline in different contexts. Furthermore, we proposed a coverage-guided search algorithm to efficiently generate test suites. Experimental results highlight the effectiveness of our approach in uncovering numerous erroneous behaviors in contexts such as medical image diagnosis and Android malware detection. This approach significantly enhances the robustness of DL models by considering the structural aspects of the DL pipeline. Copyright 2023 KICS.
This paper proposes new modeling of autonomous devices in Internet of Things (IoT) using extended Hybrid Petri nets (xHPN). This formulation uses the continuous concept of battery recharge and discharge instead quanti...
详细信息
Considering the importance of higher-dimensional equations that are widely applied to real nonlinear problems,many(4+1)-dimensional integrable systems have been established by uplifting the dimensions of their corresp...
详细信息
Considering the importance of higher-dimensional equations that are widely applied to real nonlinear problems,many(4+1)-dimensional integrable systems have been established by uplifting the dimensions of their corresponding lower-dimensional integrable ***,an integrable(4+1)-dimensional extension of the Boiti-Leon-Manna-Pempinelli(4DBLMP)equation has been proposed,which can also be considered as an extension of the famous Korteweg-de Vries equation that is applicable in fluids,plasma physics and so *** is shown that new higher-dimensional variable separation solutions with several arbitrary lowerdimensional functions can also be obtained using the multilinear variable separation approach for the 4DBLMP *** addition,by taking advantage of the explicit expressions of the new solutions,versatile(4+1)-dimensional nonlinear wave excitations can be *** an illustration,periodic breathing lumps,multi-dromion-ring-type instantons,and hybrid waves on a doubly periodic wave background are discovered to reveal abundant nonlinear structures and dynamics in higher dimensions.
In current in situ X-ray diffraction(XRD)techniques,data generation surpasses human analytical capabilities,potentially leading to the loss of *** techniques require human intervention,and lack the performance and ada...
详细信息
In current in situ X-ray diffraction(XRD)techniques,data generation surpasses human analytical capabilities,potentially leading to the loss of *** techniques require human intervention,and lack the performance and adaptability required for material *** the critical need for high-throughput automated XRD pattern analysis,we present a generalized deep learning model to classify a diverse set of materials’crystal systems and space *** our approach,we generate training data with a holistic representation of patterns that emerge from varying experimental conditions and crystal *** also employ an expedited learning technique to refine our model’s expertise to experimental *** addition,we optimize model architecture to elicit classification based on Bragg’s Law and use evaluation data to interpret our model’s *** evaluate our models using experimental data,materials unseen in training,and altered cubic crystals,where we observe state-of-the-art performance and even greater advances in space group classification.
暂无评论