Training of phase-based neurons

Complex-Valued Neural Networks are extensions of the classical Neural Networks. They have complex-valued weights, accept complex inputs and have more computational power than the classical ones. We discuss in this paper the training for Phase-Based Neurons, neural processing elements similar to Univ...

Full description

Saved in:
Bibliographic Details
Main Authors: Pavaloiu, I-B, Vasile, A., Cristea, P. D.
Format: Conference Proceeding
Language:English
Subjects:
Bioinformatics
Biological neural networks
Complex-Valued Neural Networks
Genomics
Indexes
Neurons
Phase-Based Neuron
Signal processing
Training
Universal Binary Neuron
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Complex-Valued Neural Networks are extensions of the classical Neural Networks. They have complex-valued weights, accept complex inputs and have more computational power than the classical ones. We discuss in this paper the training for Phase-Based Neurons, neural processing elements similar to Universal Binary Neurons, that uses as weights and bias complex numbers with unit magnitude, the phase being the only tunable parameter.
ISSN:2157-8672