Richard Wei

Thanks for listing these!

Thanks for the checklist @jon-tow !

Yes, good point. Updated.

Randomly, I feel Swift JIRA would be a better fit for this issue, since no change in this repo is necessary for the intended task to complete.

Ok, thanks for the context!

Definitely, they are on our roadmap. Thanks for opening an issue about this. And, contributions are welcome!

FWIW, here's an example RNN implemented using the Swift of TensorFlow Deep Learning Library: https://gist.github.com/rxwei/ce6644efad8f229651050e096c05ccbb. Most people are often stuck at these two things on their first try: * Defining...

Update: #80 added the `RNNCell` protocol and #71 added `SimpleRNN` and `LSTM`. We still need to add GRU and hopefully NTM.

This is a Swift 3.1 project. Migration to Swift 4 is necessary and can be a lot of work. Contributions are welcome!

The input language is the same DSL. The idea is based on tagless-final style interpreters and Lightweight Modular Staging. Here’s a paper discussing staged parser combinators built using LMS: https://infoscience.epfl.ch/record/203076/files/p637-jonnalagedda.pdf