Fully Complex-Valued Dendritic Neuron Model
Document Type
Article
Publication Date
4-1-2023
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.
Identifier
85114727453 (Scopus)
Publication Title
IEEE Transactions on Neural Networks and Learning Systems
External Full Text Location
https://doi.org/10.1109/TNNLS.2021.3105901
e-ISSN
21622388
ISSN
2162237X
PubMed ID
34487498
First Page
2105
Last Page
2118
Issue
4
Volume
34
Grant
2018AAA0101203
Fund Ref
National Key Research and Development Program of China
Recommended Citation
Gao, Shangce; Zhou, Meng Chu; Wang, Ziqian; Sugiyama, Daiki; Cheng, Jiujun; Wang, Jiahai; and Todo, Yuki, "Fully Complex-Valued Dendritic Neuron Model" (2023). Faculty Publications. 1828.
https://digitalcommons.njit.edu/fac_pubs/1828
