Support Vectors Machine library in .net with CUDA support. Library includes GPU SVM solver for kernels linear,RBF,Chi-Square and Exp Chi-Square which use NVIDIA CUDA technology. It allows for classification of feature rich sparse datasets through utilization of sparse matrix formats CSR, Ellpack-R or Sliced EllR-T. The use of sparse formats allowed for classification of RCV1 or Newsgroup20.
Key Features: .Net implementation, SVM CUDA acceleration – kernels and solver, Parallel kernel implementation, CUDA SVM with sparse data formats: CSR, Ellpack-R, Sliced-Ellpack.
- Changes to previous version:
Initial Announcement on mloss.org.
No one has posted any comments yet. Perhaps you'd like to be the first?
Leave a comment
You must be logged in to post comments.