Fully tensorial approach to hypercomplex neural networks

Fully tensorial theory of hypercomplex neural networks is given. The key point is to observe that the algebra multiplication can be represented as a rank three tensor. This approach is attractive for neural network libraries that support effective tensorial operations.

@article{niemczynowicz2025_2407.00449,
  title={ Fully tensorial approach to hypercomplex neural networks },
  author={ Agnieszka Niemczynowicz and Radosław Antoni Kycia },
  journal={arXiv preprint arXiv:2407.00449},
  year={ 2025 }
}