Zafarali Ahmed

Also there a many different unexpected identifiers/character/number errors in your code. Picture attached below:  

@iron-lion I think Subsets work but they don't fix the overall problem of sorting. I think we might be able to break it down into the following categories: - Bioinformatics...

This is where the loss is being calculated. If you look at the algorithm presented in [Suttons book (page 289)](http://incompleteideas.net/book/the-book-2nd.html) it is slightly different from what is given here which...

Can you use a Tuple instead?

Hi! You can explicitly check for vanishing gradient by inspecting the gradients, it does seem like your sequence length is long but not too long that and LSTM might fail,...

This is possible in theory if your sentences are of different lengths, but in general, we pad our sentences so that they are all of the same lengths to take...

You could try to change the type of the weights to tf.float16 or something with lower precision to save memory.

Why is the shape (None,..)? Keras takes into account the batch size internally! On Wed, Dec 6, 2017 at 4:51 AM Basma BOUSSAHA wrote: > Here is a small code...

Ok. Have you tried using the graph API instead of sequential? On Wed, Dec 6, 2017 at 7:24 AM Basma BOUSSAHA wrote: > No sure no, this is what is...

A good intro is here: https://keras.io/getting-started/functional-api-guide/ I believe that the sequential API is just there for legacy purposes and should not be used anymore. This is an example of me...