| Popis: |
k-Nearest Neighbor (k-NN) is a well-known classification algorithm used in many machine learning applications. When the input data size of k-NN algorithm increases, the execution time of the algorithm increases significantly. Therefore, this becomes a bottleneck for practical usage. Since k-NN algorithm is using searching, sorting and other parallelly executable tasks, we have implemented the k-NN algorithm on a GPU using CUDA utilizing the parallel tasks. The results were promising as expected and for 43,500 training records and 14,500 testing records with nine attributes, the GPU execution showed about a 100× faster execution time compared to a CPU version. |
