Differentiable Neural Computer

TensorFlow 2 implementation of a Differentiable Neural Computer (DNC) with LSTM controller as defined in Hybrid computing using a neural network with dynamic external memory.

Install by cloning the repository:

git clone git@github.com:arnaudvl/differentiable-neural-computer.git

Dependencies:

numpy
tensorflow>=2

The example notebook illustrates how to train the DNC, defined in model.py.