Zobrazeno 1 - 10
of 6 557
pro vyhledávání: '"Wijeratne, A"'
Sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP) is the bottleneck kernel of sparse tensor decomposition. In this work, we propose a GPU-based algorithm design to address the key challenges in accelerating spMTTKRP computation, including
Externí odkaz:
http://arxiv.org/abs/2405.08470
Synthetic Aperture Radar (SAR) images are commonly utilized in military applications for automatic target recognition (ATR). Machine learning (ML) methods, such as Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN), are frequently us
Externí odkaz:
http://arxiv.org/abs/2401.02687
Autor:
Gunarathna, Chathuri, Yang, Rebecca, Wijeratne Mudiyanselage, Pabasara, Amarasinghe, Gayashan, Samarasinghalage, Tharushi, Weerasinghe, R.P. Nilmini, Zhao, Hongying, Zhang, Chaoxiang, Liu, Chengyang, Wang, Kaige, Dev Sureshkumar Jayakumari, Sujan
Publikováno v:
Smart and Sustainable Built Environment, 2023, Vol. 13, Issue 4, pp. 828-855.
Externí odkaz:
http://www.emeraldinsight.com/doi/10.1108/SASBE-08-2022-0173
Sparse Matricized Tensor Times Khatri-Rao Product (spMTTKRP) is the most time-consuming compute kernel in sparse tensor decomposition. In this paper, we introduce a novel algorithm to minimize the execution time of spMTTKRP across all modes of an inp
Externí odkaz:
http://arxiv.org/abs/2309.09131
Graph Neural Networks (GNNs) have revolutionized many Machine Learning (ML) applications, such as social network analysis, bioinformatics, etc. GNN inference can be accelerated by exploiting data sparsity in the input graph, vertex features, and inte
Externí odkaz:
http://arxiv.org/abs/2308.02749
Publikováno v:
Environmental Microbiome, Vol 19, Iss 1, Pp 1-28 (2024)
Abstract Background The rhizosphere microbiome displays structural and functional dynamism driven by plant, microbial, and environmental factors. While such plasticity is a well-evidenced determinant of host health, individual and community-level mic
Externí odkaz:
https://doaj.org/article/791e1748ea9d4eb0917444a21d661c99
Autor:
Wen Luo, Hai Hoang, Katherine E. Miller, Hongwen Zhu, Serena Xu, Xiaokui Mo, Elizabeth A. R. Garfinkle, Heather Costello, Saranga Wijeratne, Wiebke Chemnitz, Ronan Gandhi, Yanling Liao, Janet Ayello, Aliza Gardenswartz, Jeremy M. Rosenblum, Kevin A. Cassady, Elaine R. Mardis, Dean A. Lee, Timothy P. Cripe, Mitchell S. Cairo
Publikováno v:
Journal of Experimental & Clinical Cancer Research, Vol 43, Iss 1, Pp 1-17 (2024)
Abstract Background Macrophages play important roles in phagocytosing tumor cells. However, tumors escape macrophage phagocytosis in part through the expression of anti-phagocytic signals, most commonly CD47. In Ewing sarcoma (ES), we found that tumo
Externí odkaz:
https://doaj.org/article/ef612054309d4f2fb16fbb5249bba11b
Synthetic Aperture Radar (SAR) Automatic Target Recognition (ATR) is the key technique for remote sensing image recognition. The state-of-the-art works exploit the deep convolutional neural networks (CNNs) for SAR ATR, leading to high computation cos
Externí odkaz:
http://arxiv.org/abs/2305.07119
Autor:
Wijeratne, Yudhanjaya, Marikar, Ishan
Low-rank adaptation (LoRA) and question-answer datasets from large language models have made it much easier for much smaller models to be finetuned to the point where they display sophisticated conversational abilities. In this paper, we present Eluw
Externí odkaz:
http://arxiv.org/abs/2304.12370
Publikováno v:
The Journal of Headache and Pain, Vol 25, Iss 1, Pp 1-3 (2024)
Externí odkaz:
https://doaj.org/article/a0906990947e44abb48ecbd7bb82f91a