To address the problems of complex real voice feature distribution, easy overfitting by learning only one classification boundary, and poor generalization ability of existing voice spoofing detection methods for unkno...
详细信息
With the development of high-performance computing,it is possible to solve large-scale computing ***,the irregularity and access characteristics of computing problems bring challenges to the realisation and performanc...
详细信息
With the development of high-performance computing,it is possible to solve large-scale computing ***,the irregularity and access characteristics of computing problems bring challenges to the realisation and performance *** the performance of a single core makes it challenging to maintain Moore's law,and multi-core processors emerge.A chip brings together multiple universal processor cores of equal status and has the same structure supported by an isomorphic multi-core *** high-performance computing,the granularity of computing tasks leads to the complexity of scheduling *** high system performance,load balancing and processor fault tolerance at a minimum cost is the key to task scheduling in the high-performance field,especially in specific multi-core hardware *** this study,global real-time task scheduling is implemented in a high-performance multi-core *** system adopts the hybrid scheduling among clusters and the intelligent fitting within clusters to implement the global real-time task scheduling *** the cluster scheduling policy,tasks are allowed to preempt the core with low priority,and the priority of tasks that access memory is dynamically improved,higher than that of all the tasks without memory *** intelligent fitting method is also *** the data read by the task is in the cache and the cache access ability value of the task is within a reasonable threshold,the priority of the task is promoted to the highest priority,pre-empting the core without the access memory *** results show that the intelligently fitting global scheduling strategy for multi-core systems has better performance in the nuclear utilisation rate and task schedulability.
End-to-end training has emerged as a prominent trend in speech recognition, with Conformer models effectively integrating Transformer and CNN architectures. However, their complexity and high computational cost pose d...
详细信息
The functional diversity index of a phytoplankton body has gradually become a new mean of measuring and *** explore the response of phytoplankton taxonomy and the functional diversity index to interannual environmenta...
详细信息
The functional diversity index of a phytoplankton body has gradually become a new mean of measuring and *** explore the response of phytoplankton taxonomy and the functional diversity index to interannual environmental changes,a survey on the structure of the phytoplankton community and water physicochemical characteristics of the water was carried out at 28 sampling points in the harbin section of the Songhua River for three consecutive years in every May from 2021 to *** taxonomy diversity index and the functional diversity index were ***,The relationship between the structure of the characteristics of the community and environmental factors was explored;secondly,we reveal the responses of taxonomic and functional diversity indices to different habitats between years;finally,we explore the main environmental factors that control the taxonomic and functional diversity indices of *** show that,initially,environmental factors in water changes caused by different water levels between years affected the composition of phytoplankton ***,by comparing the taxonomic diversity index and the functional diversity index on a time scale,we found that the taxonomic diversity index was more responsive to environmental ***,the main environmental factors on the phytoplankton taxonomic diversity index were dissolved oxygen,Taxonomic diversity index,and specific conductivity,and the main environmental factors that affected the functional diversity index were dissolved oxygen,turbidity,and water *** study reveals the important role of the taxonomic diversity index in river water quality evaluation,obtained new information on the relative precision of the taxonomic diversity index and the functional diversity index in the evaluation of ecological health of the water,and provided a reliable tool for monitoring river water quality based on aquatic organisms.
With the advent of cloud computing, many organizations, institutions, and individuals have chosen to store their data in the cloud as a way to compensate for limited local storage capabilities and reduce expenses. How...
详细信息
Deep learning-based semantic segmentation of airborne laser scanning (ALS) point clouds receives extensive attention from researchers in the field of remote sensing and computing. However, due to the special propertie...
详细信息
Event-based computation has recently gained increasing research interest for applications of vision recogni-tion due to its intrinsic advantages on efficiency and ***,the existing event-based models for vision recogni...
详细信息
Event-based computation has recently gained increasing research interest for applications of vision recogni-tion due to its intrinsic advantages on efficiency and ***,the existing event-based models for vision recogni-tion are faced with several issues,such as large network complexity and expensive training *** this paper,we propose an improved multi-liquid state machine(M-LSM)method for high-performance vision ***,we intro-duce two methods,namely multi-state fusion and multi-liquid search,to optimize the liquid state machine(LSM).Multi-state fusion by sampling the liquid state at multiple timesteps could reserve richer spatiotemporal *** adapt network architecture search(NAS)to find the potential optimal architecture of the multi-liquid state *** also train the M-LSM through an unsupervised learning rule spike-timing dependent plasticity(STDP).Our M-LSM is evalu-ated on two event-based datasets and demonstrates state-of-the-art recognition performance with superior advantages on network complexity and training cost.
Feature extraction of point clouds is a fundamental component of three-dimensional(3D)vision *** existing feature extraction networks primarily focus on enhancing the geometric perception abilities of networks and ove...
详细信息
Feature extraction of point clouds is a fundamental component of three-dimensional(3D)vision *** existing feature extraction networks primarily focus on enhancing the geometric perception abilities of networks and overlook the crucial role played by *** instance,though two airplane wings share the same shape,it demands distinct feature representations due to their differing *** this paper,we introduce a novel module called position aware module(PAM)to leverage the coordinate features of points for positional encoding,and integrating this encoding into the feature extraction network to provide essential positional ***,we embed PAM into the Point Net++framework,and design a novel feature extraction network,named Point Net *** validate the effectiveness of Point Net V3,we conducted comprehensive experiments including classification,object tracking and object detection on point *** results of remarkable improvement in three tasks demonstrate the exceptional performance achieved by Point Net V3 in point cloud processing.
Given the high prevalence of colon diseases, it is crucial to utilize computer vision technology for precise polyp segmentation during colonoscopy. However, manual detection becomes increasingly challenging due to the...
详细信息
The Processing-In-Memory (PIM) architecture becomes a promising candidate for deep learning accelerators by integrating computation and memory. Most PIM-based studies improve the performance and energy efficiency by u...
详细信息
The Processing-In-Memory (PIM) architecture becomes a promising candidate for deep learning accelerators by integrating computation and memory. Most PIM-based studies improve the performance and energy efficiency by using the Weight Stationary (WS) data flow due to its high parallelism. However, the WS data flow has some fundamental limitations. First, the WS data flow has huge activation movements between on-chip memory and off-chip memory due to the limited memory space of the ReRAM array. Second, the WS data flow needs to read the input activation repeatedly according to the convolution window. These data movements decrease the energy efficiency and performance of the PIM architecture. To address these issues, the IS data flow stores activations instead of weights to reduce data movements. But the IS data flow faces some challenges. First, the data dependency between adjacent layers limits the performance. Second, there are huge across-array computations due to the special mapping method. Third, the previous IS data flow cannot realize the high parallelism. Fourth, the IS data flow depends on the three-dimensional (3D) ReRAM structure. To address these issues, we propose a novel data flow for PIM architectures. We optimize the IS data flow to decrease the activation movement and propose a parallel computing method to realize high parallelism and reduce the across-array computations. We identify and analyze the fundamental limitations and impact of different inter-layer data flows, including the WS-WS, IS-IS, WS-IS, and IS-WS. We also propose a method to build a hybrid data flow by combining these inter-layer data flows to trade-off performance and energy consumption. Our experimental results and analysis demonstrate the potential of our design. The performance and energy efficiency of our design reaches 0.13 TFLOPS∼1.77 TFLOPS and 61 TOPS/J∼85 TOPS/J, respectively. Compared to the state-of-the-art design, the NEBULA, our design can improve performance by 1.4×, 2.
暂无评论