English

KHNNs: hypercomplex neural networks computations via Keras using TensorFlow and PyTorch

Machine Learning 2025-05-26 v1 Artificial Intelligence Neural and Evolutionary Computing

Abstract

Neural networks used in computations with more advanced algebras than real numbers perform better in some applications. However, there is no general framework for constructing hypercomplex neural networks. We propose a library integrated with Keras that can do computations within TensorFlow and PyTorch. It provides Dense and Convolutional 1D, 2D, and 3D layers architectures.

Cite

@article{arxiv.2407.00452,
  title  = {KHNNs: hypercomplex neural networks computations via Keras using TensorFlow and PyTorch},
  author = {Agnieszka Niemczynowicz and Radosław Antoni Kycia},
  journal= {arXiv preprint arXiv:2407.00452},
  year   = {2025}
}
R2 v1 2026-06-28T17:23:39.576Z