Accelerating FCM neural network classifier using graphics processing units with CUDA

With the advancement in experimental devices and approaches, scientific data can be collected more easily. Some of them are huge in size. The floating centroids method (FCM) has been proven to be a high performance neural network classifier. However, the FCM is difficult to learn from a large data set, which restricts its practical application. In this study, a parallel floating centroids method (PFCM) is proposed to speed up the FCM based on the Compute Unified Device Architecture, especially for a large data set. This method performs all stages as a batch in one block. Blocks and threads are responsible for evaluating classifiers and performing subtasks, respectively. Experimental results indicate that the speed and accuracy are improved by employing this novel approach.