| Age | Commit message (Collapse) | Author | |
|---|---|---|---|
| 47 hours | Went back up to 1986 weights | tslil | |
| 47 hours | Fixed minimax (!), fixed bugs in tak.c | tslil | |
| With minimax of depth 1 the evaluation function seems alright with the current method of training and generating weights | |||
| 47 hours | Auto-generating weights | tslil | |
| 47 hours | Generate the correct format directly | tslil | |
| 47 hours | one output (of course), Pade approximant of logistic for activation | tslil | |
| 47 hours | Working version of this script | tslil | |
| 47 hours | Also this was wrong | tslil | |
| 47 hours | Two inputs to model, stacks and flat counts | tslil | |
| 47 hours | Magic | tslil | |
| 47 hours | Closing in on something reasonable for roads | tslil | |
| 47 hours | On the hunt for a better representation | tslil | |
| 47 hours | Experimenting with training nn | tslil | |
