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)
- Python 2.7 or Python 3.3+
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.
Taehoon Kim / @carpedm20