Timeline for Intuitive description for training of LSTM (with forget gate/peephole)?
Current License: CC BY-SA 3.0
10 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| Sep 22, 2015 at 9:11 | comment | added | Brian Jack | at this point I'm avoiding backprop for an evolutionary/mutagen training algorithm just because the calculus for the backprop looks a bit scary. I tried a small test text prediction problem with a backpropMinus lstm in PyBrain but it was having trouble on convergence even with only a mere 3-character input sequence - mutational training and fitness culling (on MSE of output error over training population) might allow more creative search area analysis | |
| Sep 22, 2015 at 9:05 | comment | added | Brian Jack | PS: could someone decode those epsilons and deltas in the appendix maybe down to something I might understand with only first year calculus? | |
| Sep 22, 2015 at 8:54 | comment | added | Brian Jack | some references that might assist you: lstm.iupr.com/files nntutorial-lstm.pdf on that page may be of particular help here | |
| Sep 20, 2015 at 22:18 | answer | added | Brian Jack | timeline score: 1 | |
| Jun 22, 2015 at 12:36 | history | tweeted | twitter.com/#!/StackCompSci/status/612962435155296256 | ||
| Jun 26, 2013 at 10:55 | comment | added | Gilles 'SO- stop being evil' | This is a very large question which might be intimidating some readers. I suggest splitting it into several pieces (each of your bullet points, perhaps). Also, this topic bridges Computer Science and Cross Validated; you might consider asking about the more CS-related aspects here on Computer Science and the more statistics-related apsects on Cross Validated (but please do not post the same question on both sites). | |
| Jun 26, 2013 at 10:53 | history | edited | Gilles 'SO- stop being evil' | CC BY-SA 3.0 |
added 27 characters in body; edited title
|
| Jun 24, 2013 at 17:24 | review | First posts | |||
| Jun 24, 2013 at 23:27 | |||||
| Jun 24, 2013 at 17:21 | history | edited | Gina | CC BY-SA 3.0 |
added 313 characters in body
|
| Jun 24, 2013 at 17:04 | history | asked | Gina | CC BY-SA 3.0 |