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
-
yes, presumably a multi-layer perceptron on top of the concat should capture this to some extent.
if you want to use Keras, easy way is to do the complicated splitting in Numpy & use a multi-input model.
-
-
i like the keras api for the "standardized" use cases. Trying to think how something like it can be extended to less standard.
-
will it keep track of the gradients if I switch to numpy in the middle? How?
- 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.