A note on the complex and bicomplex valued neural networks

2022/02/04 by Daniel Alpay, Alpay, Daniel, Kamal Diki +3 · 1 citation
Computer Science · #30G35 #47A57 #68Q32 #68T07 #Blind Source Separation Techniques #F.2.1 #FOS: Computer and information sciences #FOS: Mathematics #Fuzzy Logic and Control Systems #Information Theory (cs.IT) #Machine Learning (cs.LG) #Neural Networks and Applications #Optimization and Control (math.OC)

paper · pdf · doi:10.48550/arxiv.2202.02354

openalex publication_date 2022/02/04 · openalex created_date 2025/10/10 · openalex updated_date 2026/08/04

Abstract

In this paper we first write a proof of the perceptron convergence algorithm for the complex multivalued neural networks (CMVNNs). Our primary goal is to formulate and prove the perceptron convergence algorithm for the bicomplex multivalued neural networks (BMVNNs) and other important results in the theory of neural networks based on a bicomplex algebra.

Cited by

• Classification of Principle 3D Slices of Filled-in Julia Sets in Multicomplex Spaces

Related

• Reparameterized Complex-valued Neurons Can Efficiently Learn More than Real-valued Neurons via Gradient Descent
• Universal Approximation Theorem for Vector- and Hypercomplex-Valued Neural Networks
• Two Bicomplex and One Multicomplex Least Mean Square algorithms
• Complex-valued Neural Networks -- Theory and Analysis
• Theory and Implementation of Complex-Valued Neural Networks