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

TL;DR

This paper introduces KHNNs, a library integrated with Keras, enabling hypercomplex neural network computations within TensorFlow and PyTorch, supporting various layer architectures for advanced algebraic operations.

Contribution

The paper presents a general framework and a library for constructing hypercomplex neural networks in Keras, compatible with TensorFlow and PyTorch.

Findings

Supports Dense and Convolutional layers in multiple dimensions

Facilitates hypercomplex neural network development

Enhances performance in applications using advanced algebras

Abstract

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.