A more efficient approach

Hi @carpedm20,

your code helped me a lot when I was just starting to understand NTMs and I am therefore very grateful for your contribution.

Recently, I found out about the Differential Neural Computer implementation from [Mostafa-Samir](https://github.com/Mostafa-Samir/DNC-tensorflow). He approaches the problem of having different sequence lengths in a different way using some dynamic functions provided by TensorFlow. This code, clearly, results to be more efficient than the reference code you have provided.

I decided to replicate the NTM implementation following the same approach and I ended up with [this](https://github.com/camigord/Neural-Turing-Machine). I have made the proper references to your code and approach. I hope you don't mind.

Best,

No target file, test, or entry point is identified. Read the existing NTM-tensorflow implementation and compare it with the referenced DNC-tensorflow and Neural-Turing-Machine projects; a concrete scope and acceptance criteria are needed before work can be considered done.

Written by the indexing model from the issue text.