Facebook AI Research Sequence-to-Sequence Toolkit written in Python
...Criterions compute the loss function given the model outputs and targets. Tasks store dictionaries and provide helpers for loading/iterating over Datasets, initializing the Model/Criterion and calculating the loss.
A TensorFlow implementation of the Differentiable Neural Computer
...This allows the model to learn how to store and retrieve information across long time horizons, much like a traditional computer. The architecture consists of modular components including an access module for managing memory operations, a controller (often an LSTM or feedforward network) for issuing read/write commands, and submodules for temporal linkage and memory allocation tracking.