Timeline for Neural Nets, Lasso regularization
Current License: CC BY-SA 3.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 8, 2017 at 16:36 | comment | added | Pedro Tabacof | @sfotiadis Honestly I have no idea what I meant back then, that was nearly three years ago. I removed that sentence to avoid confusion. Note that sparse autoencoders have fallen out of fashion. Variational autoencoders, which are more popular today, do use the KL divergence in its objective function, but they do not generate sparse representations. | |
| Sep 8, 2017 at 16:34 | history | edited | Pedro Tabacof | CC BY-SA 3.0 |
deleted 33 characters in body
|
| Sep 8, 2017 at 4:54 | comment | added | sfotiadis | Hi. What do you mean by "usually it's the KL divergence"? | |
| Feb 3, 2015 at 17:45 | vote | accept | Ramalho | ||
| Feb 3, 2015 at 16:32 | history | answered | Pedro Tabacof | CC BY-SA 3.0 |