English

Zenkai -- Framework For Exploring Beyond Backpropagation

Machine Learning 2023-11-17 v1

Abstract

Zenkai is an open-source framework designed to give researchers more control and flexibility over building and training deep learning machines. It does this by dividing the deep learning machine into layers of semi-autonomous learning machines with their own target and learning algorithm. This is to allow researchers greater exploration such as the use of non-differentiable layers or learning algorithms beyond those based on error backpropagation. Backpropagation Rumelhart et al. [1986] has powered deep learning to become one of the most exciting fields of the 21st century. As a result, a large number of software tools have been developed to support efficient implementation and training of neural networks through the use of backpropa- gation. While these have been critical to the success of deep learning, building frameworks around backpropagation can make it challenging to implement solutions that do not adhere to it. Zenkai aims to make it easier to get around these limitations and help researchers more easily explore new frontiers in deep learning that do not strictly adhere to the backpropagation framework.

Keywords

Cite

@article{arxiv.2311.09663,
  title  = {Zenkai -- Framework For Exploring Beyond Backpropagation},
  author = {Greg Short},
  journal= {arXiv preprint arXiv:2311.09663},
  year   = {2023}
}

Comments

14 pages. Source code available at https://www.github.com/short-greg/zenkai with documentation at https://zenkai.readthedocs.io/en/latest/. Can be installed with pip install zenkai

R2 v1 2026-06-28T13:23:05.181Z