Documentation	Build Status	Julia	Testing

RecurrentLayers.jl

RecurrentLayers.jl extends Flux.jl recurrent layers offering by providing implementations of bleeding edge recurrent layers not commonly available in base deep learning libraries. It is designed for a seamless integration with the larger Flux ecosystem, enabling researchers and practitioners to leverage the latest developments in recurrent neural networks.

Features 🚀

Currently available cells:

• Minimal gated unit (MGU) arxiv
• Light gated recurrent unit (LiGRU) arxiv
• Independently recurrent neural networks (IndRNN) arxiv
• Recurrent addictive networks (RAN) arxiv
• Recurrent highway network (RHN) arixv
• Light recurrent unit (LightRU) pub
• Neural architecture search unit (NAS) arxiv
• Evolving recurrent neural networks (MUT1/2/3) pub
• Structurally constrained recurrent neural network (SCRN) arxiv
• Peephole long short term memory (PeepholeLSTM) pub
• FastRNN and FastGRNN arxiv

Currently available wrappers:

• Stacked RNNs
• FastSlow RNNs arxiv

Installation 💻

You can install RecurrentLayers using either of:

using Pkg
Pkg.add("RecurrentLayers")

julia> ]
pkg> add RecurrentLayers

Getting started 🛠️

The workflow is identical to any recurrent Flux layer: just plug in a new recurrent layer in your workflow and test it out!

License 📜

This project is licensed under the MIT License, except for nas_cell.jl, which is licensed under the Apache License, Version 2.0.

• nas_cell.jl is a reimplementation of the NASCell from TensorFlow and is licensed under the Apache License 2.0. See the file header and LICENSE-APACHE for details.
• All other files are licensed under the MIT License. See LICENSE-MIT for details.

Support 🆘

If you have any questions, issues, or feature requests, please open an issue or contact us via email.