The von Neumann bottleneck in conventional computing architectures presents a significant challenge for data-inten-sive artificial intelligence applications.A promising approach involves designing specialized hardware...The von Neumann bottleneck in conventional computing architectures presents a significant challenge for data-inten-sive artificial intelligence applications.A promising approach involves designing specialized hardware with on-chip parameter tunability,which directly accelerates machine learning functions.This work demonstrates a continuously tunable mixed-kernel function physically realized within a van der Waals heterostructure.We designed and fabricated a MoTe_(2)/MoS_(2)type-Ⅱvertical heterojunction phototransistor,which exhibits a non-monotonic,Gaussian-like optoelectronic response owing to its unique inter-layer charge transfer mechanism.This intrinsic physical behavior directly maps to a mixed-kernel function combining Gaussian and Sigmoid characteristics.Furthermore,the hardware kernel can be continuously modulated by in-situ tuning of external opti-cal stimuli.The mixed-kernel exhibited exceptional performance,achieving precision,accuracy,and area under the curve(AUC)values of 95.8%,96%,and 0.9986,respectively,significantly outperforming conventional kernels.By successfully embedding a complex,adaptable mathematical function into the intrinsic physical properties of a single device,this work pioneers a novel pathway toward next-generation,energy-efficient intelligent systems with hardware-level adaptability.展开更多
Classification and association rule mining are used to take decisions based on relationships between attributes and help decision makers to take correct decisions at right time. Associative classification first genera...Classification and association rule mining are used to take decisions based on relationships between attributes and help decision makers to take correct decisions at right time. Associative classification first generates class based association rules and use that generate rule set which is used to predict the class label for unseen data. The large data sets may have many null-transac- tions. A null-transaction is a transaction that does not contain any of the itemsets being examined. It is important to consider the null invariance property when selecting appropriate interesting measures in the correlation analysis. Real time data set has mixed attributes. Analyze the mixed attribute data set is not easy. Hence, the proposed work uses cosine measure to avoid the influence of null transactions during rule generation. It employs mixed-kernel probability density function (PDF) to handle continuous attributes during data analysis. It has ably to handle both nominal and continuous attributes and generates mixed attribute rule set. To explore the search space efficiently it applies Ant Colony Optimization (ACO). The public data sets are used to analyze the performance of the algorithm. The results illustrate that the support-confidence framework with a correlation measure generates more accurate simple rule set and discover more interesting rules.展开更多
基金co-supported by the National Natural Science Foundation of China(Grant Nos.62222404,T2450054,62304084,62504087,62361136587 and 92248304)the National Key Research and Development Plan of China(Grant No.2021YFB3601200)+3 种基金the Major Program of Hubei Province(Grant No.2023BAA009)the Research Grants Council of Hong Kong Postdoctoral Fellowship Scheme(Grant No.PDFS2223-4S06)the China Postdoctoral Science Foundation funded project(Grant No.2025M770530)the Postdoctoral Fellowship Program of CPSF(Grant No.GZB20250136).
文摘The von Neumann bottleneck in conventional computing architectures presents a significant challenge for data-inten-sive artificial intelligence applications.A promising approach involves designing specialized hardware with on-chip parameter tunability,which directly accelerates machine learning functions.This work demonstrates a continuously tunable mixed-kernel function physically realized within a van der Waals heterostructure.We designed and fabricated a MoTe_(2)/MoS_(2)type-Ⅱvertical heterojunction phototransistor,which exhibits a non-monotonic,Gaussian-like optoelectronic response owing to its unique inter-layer charge transfer mechanism.This intrinsic physical behavior directly maps to a mixed-kernel function combining Gaussian and Sigmoid characteristics.Furthermore,the hardware kernel can be continuously modulated by in-situ tuning of external opti-cal stimuli.The mixed-kernel exhibited exceptional performance,achieving precision,accuracy,and area under the curve(AUC)values of 95.8%,96%,and 0.9986,respectively,significantly outperforming conventional kernels.By successfully embedding a complex,adaptable mathematical function into the intrinsic physical properties of a single device,this work pioneers a novel pathway toward next-generation,energy-efficient intelligent systems with hardware-level adaptability.
文摘Classification and association rule mining are used to take decisions based on relationships between attributes and help decision makers to take correct decisions at right time. Associative classification first generates class based association rules and use that generate rule set which is used to predict the class label for unseen data. The large data sets may have many null-transac- tions. A null-transaction is a transaction that does not contain any of the itemsets being examined. It is important to consider the null invariance property when selecting appropriate interesting measures in the correlation analysis. Real time data set has mixed attributes. Analyze the mixed attribute data set is not easy. Hence, the proposed work uses cosine measure to avoid the influence of null transactions during rule generation. It employs mixed-kernel probability density function (PDF) to handle continuous attributes during data analysis. It has ably to handle both nominal and continuous attributes and generates mixed attribute rule set. To explore the search space efficiently it applies Ant Colony Optimization (ACO). The public data sets are used to analyze the performance of the algorithm. The results illustrate that the support-confidence framework with a correlation measure generates more accurate simple rule set and discover more interesting rules.
