KHNNs: hypercomplex neural networks computations via Keras using TensorFlow and PyTorch
This work addresses a niche problem for researchers and developers working with hypercomplex algebras in neural networks, but it is incremental as it builds on existing frameworks without introducing new methods.
The authors tackled the lack of a general framework for hypercomplex neural networks by proposing a library integrated with Keras that supports computations in TensorFlow and PyTorch, providing Dense and Convolutional layers for 1D, 2D, and 3D architectures.
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.