Fully Complex-valued Dendritic Neuron Model

Shangce Gao, Meng Chu Zhou, Ziqian Wang, Daiki Sugiyama, Jiujun Cheng, Jiahai Wang, Yuki Todo

Research output: Contribution to journalArticlepeer-review

Abstract

A single dendritic neuron model (DNM) that owns the nonlinear information processing ability of dendrites has been widely used for classification and prediction. Complex-valued neural networks that consist of a number of multiple/deep-layer McCulloch-Pitts neurons have achieved great successes so far since neural computing was utilized for signal processing. Yet no complex value representations appear in single neuron architectures. In this article, we first extend DNM from a real-value domain to a complex-valued one. Performance of complex-valued DNM (CDNM) is evaluated through a complex xor problem, a non-minimum phase equalization problem, and a real-world wind prediction task. Also, a comparative analysis on a set of elementary transcendental functions as an activation function is implemented and preparatory experiments are carried out for determining hyperparameters. The experimental results indicate that the proposed CDNM significantly outperforms real-valued DNM, complex-valued multi-layer perceptron, and other complex-valued neuron models.

Original languageEnglish (US)
JournalIEEE Transactions on Neural Networks and Learning Systems
DOIs
StateAccepted/In press - 2021

All Science Journal Classification (ASJC) codes

  • Software
  • Computer Science Applications
  • Computer Networks and Communications
  • Artificial Intelligence

Keywords

  • Activation functions
  • Biological neural networks
  • complex back-propagation (BP)
  • complex domain
  • complex-valued neural networks
  • Computational modeling
  • Computer architecture
  • Convergence
  • Dendrites (neurons)
  • dendritic neuron model (DNM)
  • elementary transcendental functions
  • McCulloch-Pitts neuron.
  • Neurons
  • Task analysis

Fingerprint

Dive into the research topics of 'Fully Complex-valued Dendritic Neuron Model'. Together they form a unique fingerprint.

Cite this