CudaRF: A CUDA-based Implementation of Random Forests
Blekinge Institute of Technology, School of Computing2011 (English)Conference paper (Refereed) Published
Machine learning algorithms are frequently applied in data mining applications. Many of the tasks in this domain concern high-dimensional data. Consequently, these tasks are often complex and computationally expensive. This paper presents a GPU-based parallel implementation of the Random Forests algorithm. In contrast to previous work, the proposed algorithm is based on the compute uniﬁed device architecture (CUDA). An experimental comparison between the CUDA-based algorithm (CudaRF), and state-of-the-art Random Forests algorithms (FastRF and LibRF) shows that CudaRF outperforms both FastRF and LibRF for the studied classiﬁcation task.
Place, publisher, year, edition, pages
Sharm El-Sheikh, Egypt: IEEE , 2011.
Random forests, Machine learning, Parallel computing, Graphics processing units, GPGPU
IdentifiersURN: urn:nbn:se:bth-7343Local ID: oai:bth.se:forskinfo7680811940312F67C125797C002D7E3DOAI: oai:DiVA.org:bth-7343DiVA: diva2:834950
9th ACS/IEEE Int'l Conference on Computer Systems And Applications (AICCSA 2011)