Mercurial > pylearn
comparison doc/v2_planning/neural_net.txt @ 1090:a80b296eb0df
I removed big picture from the description of the neural network committee
| author | Razvan Pascanu <r.pascanu@gmail.com> |
|---|---|
| date | Sun, 12 Sep 2010 10:54:09 -0400 |
| parents | e254065e7fd7 |
| children | aab9c261361c |
comparison
equal
deleted
inserted
replaced
| 1089:f15216356522 | 1090:a80b296eb0df |
|---|---|
| 10 | 10 |
| 11 | 11 |
| 12 Objective ( Razvan) | 12 Objective ( Razvan) |
| 13 --------- | 13 --------- |
| 14 | 14 |
| 15 Come up with a big picture of how things work together. The way I see it personaly, | 15 Come up with a description of how to write learners ( how to combine |
| 16 we should pick "random" interfaces for any component for which there is no one yet, | 16 optimizer, structure, error measure, how to talk to datasets, tasks ( if there |
| 17 and come with pseudo-code for some tasks + text describing all details. | 17 is anything like a dataset object in your view) and so on). |
| 18 o The way I see it personaly, we should pick "random" interfaces for any component | |
| 19 for which there is no one yet, or change the interface to answer our needs. | |
| 20 If our description of how these things get together. I would say come up with | |
| 21 pseudo-code for some tasks ( that vary as much as possible) + text describing | |
| 22 all the missing details. | |
| 18 | 23 |