Mercurial > pylearn
comparison doc/v2_planning/learner.txt @ 1055:bc3f7834db83
added a comment/question about Type
| author | Yoshua Bengio <bengioy@iro.umontreal.ca> |
|---|---|
| date | Wed, 08 Sep 2010 20:45:17 -0400 |
| parents | 390166ace9e5 |
| children | 19033ef1636d e342de3ae485 |
comparison
equal
deleted
inserted
replaced
| 1054:a474fabd1f37 | 1055:bc3f7834db83 |
|---|---|
| 268 whole saved model just to attach meta-info e.g. validation score. Choosing this API spills | 268 whole saved model just to attach meta-info e.g. validation score. Choosing this API spills |
| 269 over into other committees, so we should get their feedback about how to resolve it. | 269 over into other committees, so we should get their feedback about how to resolve it. |
| 270 | 270 |
| 271 Comments | 271 Comments |
| 272 ~~~~~~~~ | 272 ~~~~~~~~ |
| 273 | |
| 274 YB asks: it seems to me that what we really need from "Type" is not just | |
| 275 testing that a value is legal, but more practically a function that specifies the | |
| 276 prior distribution for the hyper-parameter, i.e., how to sample from it, | |
| 277 and possibly some representation of it that could be used to infer | |
| 278 a posterior (such as an unnormalized log-density or log-probability). | |
| 279 Having the min and max and default limits us to the uniform distribution, | |
| 280 which may not always be appropriate. For example sometimes we'd like | |
| 281 Gaussian (-infty to infty) or Exponential (0 to infty) or Poisson (non-negative integers). | |
| 282 For that reason, I think that "Type" is not a very good name. | |
| 283 How about "Prior" or "Density" or something like that? | |
| 284 | |
| 273 OD asks: (I hope it's ok to leave comments even though I'm not in committee... I'm | 285 OD asks: (I hope it's ok to leave comments even though I'm not in committee... I'm |
| 274 interested to see how the learner interface is shaping up so I'll be keeping | 286 interested to see how the learner interface is shaping up so I'll be keeping |
| 275 an eye on this file) | 287 an eye on this file) |
| 276 I'm wondering what's the benefit of such an API compared to simply defining a | 288 I'm wondering what's the benefit of such an API compared to simply defining a |
| 277 new method for each instruction. It seems to me that typically, the 'execute' | 289 new method for each instruction. It seems to me that typically, the 'execute' |