A General Framework for Hypercomplex-valued Extreme Learning Machines
This work addresses the challenge of handling high-dimensional data in machine learning by introducing hypercomplex-valued ELMs, representing an incremental advancement in neural network architectures.
The paper tackles the problem of extending extreme learning machines (ELMs) to hypercomplex algebras, proposing a framework that enables robust operations and learning via hypercomplex-valued least-squares, with experiments showing excellent performance in time-series prediction and color image auto-encoding tasks.
This paper aims to establish a framework for extreme learning machines (ELMs) on general hypercomplex algebras. Hypercomplex neural networks are machine learning models that feature higher-dimension numbers as parameters, inputs, and outputs. Firstly, we review broad hypercomplex algebras and show a framework to operate in these algebras through real-valued linear algebra operations in a robust manner. We proceed to explore a handful of well-known four-dimensional examples. Then, we propose the hypercomplex-valued ELMs and derive their learning using a hypercomplex-valued least-squares problem. Finally, we compare real and hypercomplex-valued ELM models' performance in an experiment on time-series prediction and another on color image auto-encoding. The computational experiments highlight the excellent performance of hypercomplex-valued ELMs to treat high-dimensional data, including models based on unusual hypercomplex algebras.