Timeline for Can someone help me to understand sequence-to-sequence transformation using (Wolfram-specific) recurrent neural nets?
Current License: CC BY-SA 4.0
5 events
| when toggle format | what | by | license | comment | |
|---|---|---|---|---|---|
| May 23, 2018 at 17:00 | comment | added | Euphor | If I understand correctly--and I'm still not 100% sure I do--there are basically two stages to sequence-to-sequence transformation: the encoder (sequence-to-vector) stage and the decoder (vector-to-sequence) stage. The encoder stage somehow feeds its state to the decoder stage, and the decoder always tries to make sure that any given vector (along with an associated encoder state) will result in (roughly) the same output sequence. Hopefully this is something like the right idea. | |
| May 22, 2018 at 9:12 | comment | added | Sebastian | I wrote the tutorial, and would definitely like to improve it to be more understandable (it is one of the more complicated neural net application examples...). Are there any parts of going from a vector to a sequence that you understand, or is the whole thing a complete mystery? | |
| May 19, 2018 at 13:37 | history | tweeted | twitter.com/StackMma/status/997833681430568962 | ||
| May 15, 2018 at 14:16 | review | First posts | |||
| May 15, 2018 at 19:17 | |||||
| May 15, 2018 at 14:12 | history | asked | Euphor | CC BY-SA 4.0 |