| Age | Commit message (Collapse) | Author | Files | Lines | |
|---|---|---|---|---|---|
| 2016-12-06 | add unit tests for gensvm_train | Gertjan van den Burg | 1 | -2/+0 | |
| 2016-12-05 | fix missing test in gensvm_optimize and expose doublesort | Gertjan van den Burg | 1 | -14/+45 | |
| 2016-10-24 | update copyright information | Gertjan van den Burg | 1 | -2/+21 | |
| 2016-10-14 | add sparse matrices to GenSVM and reorganize update functionality | Gertjan van den Burg | 1 | -754/+0 | |
| 2016-10-06 | Switch to using dsyrk instead of dsyr for speed. | Gertjan van den Burg | 1 | -22/+21 | |
| Also added a workspace (GenWork) structure for to hold working matrices for the gensvm_get_update() and gensvm_get_loss() functions | |||||
| 2016-09-30 | rewrite of the update function to use only rank 1 operations where possible | Gertjan van den Burg | 1 | -26/+12 | |
| 2016-09-30 | Rewrite UU matrix to be K*K*(K-1) instead of n*K*(K-1) | Gertjan van den Burg | 1 | -192/+18 | |
| significant memory reduction by turning the 3D UU matrix into a 2D block matrix, with significantly less dimensions | |||||
| 2016-09-30 | Remove category matrix from implementation | Gertjan van den Burg | 1 | -69/+5 | |
| It's a remnant from the Matlab implementation, where it actually makes sense to use. Here it becomes a significant memory burden for large datasets, and doesn't provide any speedup | |||||
| 2016-09-30 | minor changes and start on test of gensvm_optimize | Gertjan van den Burg | 1 | -2/+116 | |
| 2016-09-30 | Break up update function and add unit tests for parts | Gertjan van den Burg | 1 | -7/+461 | |
| 2016-09-22 | More unit tests for optimize | Gertjan van den Burg | 1 | -6/+694 | |
| Also added auxiliary Octave files used to construct the unit tests | |||||
| 2016-09-20 | Unit tests and corresponding data | Gertjan van den Burg | 1 | -0/+450 | |
