why LSTM word based model works better with random input seed than fixed input seed?

by Emna Jaoua   Last Updated July 04, 2018 10:19 AM

I have implemented an LSTM model that have 2 LSTM layers, a dropout layer and a dense layer for predictions. I trained my LSTM model on 1000 XML files. Each file has 4 main markups with very simple fields in between the markups. My training data was acquired using a list of sequences. The sequence length is 3 and the step window is 1.

As model parameters, I have set :

learning rate: 0.001

batch size: 65

Number of iterations: 20

So for predictions, I give my model 3 words which are 3 XML markups chosen randomly and the model should generate the 10 next markups. What I don't understand is why my model predicts accurate results when the input seed is chosen randomly while when I give it a constant input seed, it does not predict accurately.



Related Questions


Key info extraction from text

Updated January 23, 2018 20:19 PM



How to use Keras pre-trained 'Embedding' layer?

Updated December 28, 2017 18:19 PM