Mercurial > pylearn
comparison doc/v2_planning/learner.txt @ 1046:f1732269bce8
comment on Olivier's comment
| author | Razvan Pascanu <r.pascanu@gmail.com> |
|---|---|
| date | Wed, 08 Sep 2010 13:50:13 -0400 |
| parents | d57bdd9a9980 |
| children | 84f62533e7a8 |
comparison
equal
deleted
inserted
replaced
| 1045:d57bdd9a9980 | 1046:f1732269bce8 |
|---|---|
| 281 elif instruction == 'do_y': | 281 elif instruction == 'do_y': |
| 282 self.do_y(..) | 282 self.do_y(..) |
| 283 ... | 283 ... |
| 284 so why not directly call do_x / do_y instead? | 284 so why not directly call do_x / do_y instead? |
| 285 | 285 |
| 286 | |
| 287 Comment by RP | |
| 288 ~~~~~~~~~~~~~ | |
| 289 | |
| 290 James correct me if I'm wrong, but I think each instruction has a execute | |
| 291 command. The job of the learner is to traverse the graph and for each edge | |
| 292 that it decides to cross to call the execute of that edge. Maybe James has | |
| 293 something else in mind, but this was my understanding. | |
| 294 | |
| 295 | |
| 296 | |
| 286 Just another view/spin on the same idea (Razvan) | 297 Just another view/spin on the same idea (Razvan) |
| 287 ================================================ | 298 ================================================ |
| 288 | 299 |
| 289 | 300 |
| 290 My idea is probably just a spin off from what James wrote. It is an extension | 301 My idea is probably just a spin off from what James wrote. It is an extension |