I have recently begun researching LSTM networks, as I have finished my GA and am looking to progress to something more difficult. I I believe I am using the classic LSTM (if that makes any sense) and have a few questions:.
Do I need LSTM cellsunits everywhere in all cell locationthe network? Or wouldFor example, can I only use them inLSTM units for the inputfirst and output cellslast layer and use simple feedforward for the hidden neuronsunits everywhere else?
How do I go about implementing Biasbias values into aan LSTM?
Assuming I create a Networknetwork that predicts the next few words of a sentence, does that mean my outputs should be every possible word that the network could conceivably use?
Any help would be appreciated. Thanks!