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.

翻译：在采用比实数更高级代数结构的计算中，神经网络在某些应用场景表现出更优性能。然而，目前缺乏构建超复数神经网络的通用框架。本研究提出一个与Keras集成的开源库，可在TensorFlow和PyTorch环境下执行超复数计算。该库提供了全连接层及一维、二维与三维卷积层的架构实现。