Results 11 to 20 of about 21,055,470 (353)
, 2013 To define and identify a region-of-interest (ROI) in a digital image, the shape descriptor of the ROI has to be described in terms of its boundary characteristics. To address the generic issues of contour tracking, the yConvex Hypergraph (yCHG) model was
Agarwal, Tejaswi +2 more
core +3 more sources
Nested data-parallelism on the gpu [PDF]
Proceedings of the 17th ACM SIGPLAN international conference on Functional programming, 2012 Graphics processing units (GPUs) provide both memory bandwidth and arithmetic performance far greater than that available on CPUs but, because of their Single-Instruction-Multiple-Data (SIMD) architecture, they are hard to program.
Lars Bergstrom, John H. Reppy
semanticscholar +4 more sources
Quantum data parallelism in quantum neural networks
Physical Review ResearchQuantum neural networks hold promise for achieving lower generalization error bounds and enhanced computational efficiency in processing certain datasets.
Sixuan Wu, Yue Zhang, Jian Li
doaj +2 more sources
A snapshot of parallelism in distributed deep learning training
Revista Colombiana De ComputacionThe accelerated development of applications related to artificial intelligence has generated the creation of increasingly complex neural network models with enormous amounts of parameters, currently reaching up to trillions of parameters.
Hairol Romero-Sandí +2 more
exaly +3 more sources
Adaptive memory reservation strategy for heavy workloads in the Spark environment [PDF]
PeerJ Computer ScienceThe rise of the Internet of Things (IoT) and Industry 2.0 has spurred a growing need for extensive data computing, and Spark emerged as a promising Big Data platform, attributed to its distributed in-memory computing capabilities.
Bohan Li +6 more
doaj +3 more sources
Enhancing parallelism by removing cyclic data dependencies [PDF]
, 1994 D'Hollander, Erik, Zhang, Fubo
core +3 more sources
A Hybrid Tensor-Expert-Data Parallelism Approach to Optimize Mixture-of-Experts Training [PDF]
International Conference on Supercomputing, 2023 Mixture-of-Experts (MoE) is a neural network architecture that adds sparsely activated expert blocks to a base model, increasing the number of parameters without impacting computational costs.
Siddharth Singh +5 more
semanticscholar +1 more source
Accelerating Distributed SGD With Group Hybrid Parallelism
IEEE Access, 2021 The scale of model parameters and datasets is rapidly growing for high accuracy in various areas. To train a large-scale deep neural network (DNN) model, a huge amount of computation and memory is required; therefore, a parallelization technique for ...
Kyung-No Joo, Chan-Hyun Youn
doaj +1 more source
IEEE Access, 2023 Deep learning (DL) has gained increasing prominence in latency-critical artificial intelligence (AI) applications. Due to the intensive computational requirements of these applications, cloud-centric approaches have been attempted to address this issue ...
Emre Kilcioglu +2 more
doaj +1 more source
Applied Sciences, 2021 The recent unprecedented success of deep learning (DL) in various fields is underlied by its use of large-scale data and models. Training a large-scale deep neural network (DNN) model with large-scale data, however, is time-consuming.
Yunyong Ko, Sang-Wook Kim
doaj +1 more source