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.

翻译：本文提出了超复数神经网络的全张量理论。其核心在于将代数乘法表示为三阶张量。该方法对于支持高效张量运算的神经网络库具有显著优势。