A Linear Algebra Approach to C-Means Clustering Using GPUs and MPI

摘要: The fuzzy c-means clustering is a well-known unsupervised algorithm and has been widely used in various pattern recognition applications. As the amount of data increase, however, basic serial implementation becomes overwhelmed. This main motivation for utilizing computational power parallel machines to speed up algorithm. We present an that exploits mathematical equations create building blocks based on linear algebra functions are optimized most available architectures. implemented our both GPU (using CUDA CUBLAS) MPI MPI4py NumPy), then evaluated their performance scalability. Experiments show outperforms all implementations have proposed so far.