Keras makes bidirectional LSTMs easy to write (literally 3 lines). But knowing if applying them makes sense, is a different story.pic.twitter.com/qCVrpkDdmj
-
z_i = concat(LSTM(x_1,..,x_{i-1}), LSTM(x_n,...x_{i+1}))
you can do this in a few lines. You'll need a Lambda layer to split the sequences.
-
-
hmm. that's where I got stuck the last time ;)
-
it's not trivial by any means. What tools do you usually use?
- Show replies
New conversation -
Loading seems to be taking a while.
Twitter may be over capacity or experiencing a momentary hiccup. Try again or visit Twitter Status for more information.