Tensorflow implementation of Neural Turing Machine. This implementation uses an LSTM controller. NTM models with multiple read/write heads are supported.
The referenced torch code can be found here.
** 1. Loss sometimes goes to nan even with the gradient clipping (#2).** ** 2. The code is very poorly design to support NTM inputs with variable lengths. Just use this code as a reference.**
- Python 2.7 or Python 3.3+
- Tensorflow 0.12.1
- NumPy
To train a copy task:
$ python main.py --task copy --is_train True
To test a quick copy task:
$ python main.py --task copy --test_max_length 10
More detailed results can be found [here](ipynb/NTM\ Test.ipynb).
Copy task:
Recall task:
(in progress)
Taehoon Kim / @carpedm20