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

2024/06/29 by Niemczynowicz, Agnieszka, Kycia, Radosław Antoni
#Artificial Intelligence (cs.AI) #FOS: Computer and information sciences #Machine Learning (cs.LG) #Neural and Evolutionary Computing (cs.NE)

paper · doi:10.48550/arxiv.2407.00452

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.

Related

• Fully tensorial approach to hypercomplex neural networks
• Applications of Deep Neural Networks with Keras
• PHYDI: Initializing Parameterized Hypercomplex Neural Networks as Identity Functions
• Gluing Neural Networks Symbolically Through Hyperdimensional Computing
• Towards Explaining Hypercomplex Neural Networks