Timeline for Why updating only a part of all neural network weights does not work?
Current License: CC BY-SA 3.0
6 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Aug 4, 2016 at 5:01 | comment | added | Yuval Filmus | @TheLazyLog Perceptrons cannot represent all functions. | |
| Aug 4, 2016 at 1:20 | comment | added | The Lazy Log | But I mean it should at least learn to overfit the single training example, right? The problem in my network is that it just does not learn at all. I just want it to fit exactly to the training example. | |
| Aug 3, 2016 at 20:18 | history | edited | D.W.♦ | CC BY-SA 3.0 |
added 147 characters in body
|
| Aug 3, 2016 at 15:34 | comment | added | D.W.♦ | @TheLazyLog, exactly -- it doesn't learn anything because it can't -- a single-layer network can't learn much. | |
| Aug 3, 2016 at 15:22 | comment | added | The Lazy Log | Yeah, that's what I thought. But for some reasons, my neural network with single layer just does not want to learn anything. Very strange! Perhaps something wrong in code, not in the model | |
| Aug 3, 2016 at 14:31 | history | answered | Yuval Filmus | CC BY-SA 3.0 |