Neural Turing Machine in Tensorflow
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.
Known issue: Loss sometimes goes to nan even with the gradient clipping (#2)
Prerequisites
- Python 2.7 or Python 3.3+
- Tensorflow
- NumPy
Usage
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
Results
More detailed results can be found [here](ipynb/NTM\ Test.ipynb).
Copy task:
Recall task:
(in progress)
Author
Taehoon Kim / @carpedm20