| Branch | Commit message | Author | Age | |
|---|---|---|---|---|
| master | Dual arrays is >100x faster than 'ad' on large fneural | Tom Smeding | 19 hours | |
| Age | Commit message | Author | ||
| 19 hours | Dual arrays is >100x faster than 'ad' on large fneuralHEADmaster | Tom Smeding | ||
| 27 hours | WIP array stuff untested | Tom Smeding | ||
| 30 hours | WIP array AD | Tom Smeding | ||
| 43 hours | Remove redundant Num constraint on writeTape | Tom Smeding | ||
| 43 hours | Optimise by backpropagating scalar computation in C | Tom Smeding | ||
| 4 days | Working tests and benchmarks against 'ad' | Tom Smeding | ||
| 4 days | Neural returns 1 on all-zero input, not 0. | Tom Smeding | ||
| 4 days | Evaluate result Dual before backpropagating | Tom Smeding | ||
| 4 days | Nicer API for writing Dual instances | Tom Smeding | ||
| 4 days | Add (toggleable) debug code | Tom Smeding | ||
| [...] | ||||
 |
index : ad-dual | |
| [no description] | git daemon user |
| aboutsummaryrefslogtreecommitdiff |