Hacktoberfest 2026: the issues maintainers tagged for October, open and beginner-friendly. Browse Hacktoberfest issues

RNN Models

Open
#20 12 comments 0 reactions 1 assignee View on GitHub

@pavanky is already working on this.

Since Jul 23, 2017.

Assessment

This issue has not been assessed yet.

Description

feature

Once we have an implementation of the Layer Class https://github.com/arrayfire/arrayfire_ml/issues/17 , the Optimizer class and the DataSet class we can go about creating RNN flavors. There are 3 models that should be implemented:

  • Vanilla RNN
  • LSTM
  • GRU

These will require the implementation of their derivatives and their forward prop values.
Certain details to consider:

  • RNN's have a stack of weight matrices and bias' (not just 1 per Layer, thus the Layer needs to be general enough to handle this)
  • The optimization needs to be handled via two methods:
    • RTRL (real time recurrent learning) &
    • BPTT (backprop through time)

To enable the above two methods of learning we should consider inheriting from Layer and implementing a Recurrent Layer.

Dominant language
C++
Stars
105
Forks
22
No merged PRs in 30d

Contributor guide

No contributing guide indexed for this repository

First steps

  1. Read the whole issue, then the project's contributing guide.
  2. Comment on the issue to say you are picking it up — it saves two people doing the same work.
  3. Fork the repository and make your change on a branch.
  4. Open a pull request that references the issue number.

More from arrayfire/arrayfire-ml

All issues in arrayfire/arrayfire-ml

Similar issues

More C++ issues

Get new issues in your inbox

A short digest of beginner-friendly GitHub issues.