Fully tensorial approach to hypercomplex neural networks

Agnieszka Niemczynowicz, Radosław Antoni Kycia
6/29/2024
cs.LGcs.AIcs.NE

No confident code implementation found for this paper.

Abstract

Fully tensorial theory of hypercomplex neural networks is given. It allows neural networks to use arithmetic based on arbitrary algebras. The key point is to observe that algebra multiplication can be represented as a rank three tensor and use this tensor in every algebraic operation. This approach is attractive for neural network libraries that support effective tensorial operations. It agrees with previous implementations for four-dimensional algebras.

View on arXivView PDF

Code Implementations

No confident code match yet

We couldn't find an author-owned or strongly-evidenced community implementation for this paper. Any repos shown below are weak matches — verify before relying on them.

No code implementations found yet.

Know of an implementation? Let us know in the comments below!

Similar Papers

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

84% match2024

Universal Approximation Theorem for Vector- and Hypercomplex-Valued Neural Networks

81% match2024

Tensor Cookbook: Mastering Tensors through Diagrams

79% match2026

Neural Learning of Fast Matrix Multiplication Algorithms: A StrassenNet Approach

79% match2026

Graph Tensor Networks: An Intuitive Framework for Designing Large-Scale Neural Learning Systems on Multiple Domains

79% match2023

Tensor Networks Meet Neural Networks: A Survey and Future Perspectives

79% match1 repo1562023

Cite this paper

@article{niemczynowicz2024fully,
  title  = {Fully tensorial approach to hypercomplex neural networks},
  author = {Agnieszka Niemczynowicz and Radosław Antoni Kycia},
  year   = {2024},
  eprint = {2407.00449},
  archivePrefix = {arXiv},
  url    = {http://arxiv.org/abs/2407.00449v3}
}

Add a badge to your README

Shows whether official code is linked for this paper.

Code of Paper badge
[![Code of Paper](https://codeofpaper.com/badge/2407.00449.svg)](https://codeofpaper.com/paper/2407.00449)

Discussion