I’m sharing a PyTorch implementation of a neural turing machine.
I’m well aware that there are a few other implementations out there, but I think mine is quite straight forward yet extensible/generic, plus it works great. This is the result of intensive 3 weeks. Also, I documented anything worth documenting so it’ll be easy to pick up and use in external projects.
Here’s the link to github: PyTorch Neural Turing Machines (NTM)
Let me know if you find it useful or if you have any suggestions.
this looks like the cleanest implementation i’ve seen so far. thank you for sharing.
@smth, thanks for the kind words
Just a quick update, I added the repeat-copy task and the results are aligned with the paper. I also added some fixes and additional plots.
Github: PyTorch NTM
Here’s an animated GIF that shows how the network learns to predict the targets for the repeat-copy task. Specifically, the network was evaluated in each checkpoint that was saved during training (with the same input sequence).
This implementation works for time series prediction???