Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm

Authors:
Igor Aizenberg;Claudio Moraga
Affiliations:
Department of Computer and Information Sciences, Texas A&M University––Texarkana, P.O. Box 5518, 2600 N. Robison Rd., 75505, Texarkana, TX, USA;Department of Computer Science-1, University of Dortmund, P.O. Box 5518, 2600 N. Robison Rd., 44221, Dortmund, TX, Germany
Venue:
Soft Computing - A Fusion of Foundations, Methodologies and Applications
Year:
2006

Citing 0
Cited 20

Single-layered complex-valued neural network for real-valued classification problems

Neurocomputing
Ensemble of single-layered complex-valued neural networks for classification tasks

Neurocomputing
A class of discrete time recurrent neural networks with multivalued neurons

Neurocomputing
Discrete-time recurrent neural networks with complex-valued linear threshold neurons

IEEE Transactions on Circuits and Systems II: Express Briefs
A class of discrete-time recurrent neural networks with multivalued neurons

IJCNN'09 Proceedings of the 2009 international joint conference on Neural Networks
Design of neural networks

KES'07/WIRN'07 Proceedings of the 11th international conference, KES 2007 and XVII Italian workshop on neural networks conference on Knowledge-based intelligent information and engineering systems: Part I
Solving selected classification problems in bioinformatics using multilayer neural network based on multi-valued neurons (MLMVN)

ICANN'07 Proceedings of the 17th international conference on Artificial neural networks
Least-Squares Support Vector Machine Approach to Viral Replication Origin Prediction

INFORMS Journal on Computing
Complex-valued neurons with phase-dependent activation functions

ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
Periodic activation function and a modified learning algorithm for the multivalued neuron

IEEE Transactions on Neural Networks
Fast learning fully complex-valued classifiers for real-valued classification problems

ISNN'11 Proceedings of the 8th international conference on Advances in neural networks - Volume Part I
Multi-valued neurons: hebbian and error-correction learning

IWANN'11 Proceedings of the 11th international conference on Artificial neural networks conference on Advances in computational intelligence - Volume Part I
Decoding phase-based information from steady-state visual evoked potentials with use of complex-valued neural network

IDEAL'11 Proceedings of the 12th international conference on Intelligent data engineering and automated learning
A fully complex-valued radial basis function classifier for real-valued classification problems

Neurocomputing
Fast learning Circular Complex-valued Extreme Learning Machine (CC-ELM) for real-valued classification problems

Information Sciences: an International Journal
Metacognitive learning in a fully complex-valued radial basis function neural network

Neural Computation
2012 Special Issue: A meta-cognitive learning algorithm for a Fully Complex-valued Relaxation Network

Neural Networks
A new multi-valued neural network for the extraction of lumped models of analog circuits

Analog Integrated Circuits and Signal Processing
Complex-Valued neuro-fuzzy inference system based classifier

SEMCCO'12 Proceedings of the Third international conference on Swarm, Evolutionary, and Memetic Computing
System identification and modelling based on a double modified multi-valued neural network

Analog Integrated Circuits and Signal Processing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A multilayer neural network based on multi-valued neurons (MLMVN) is considered in the paper. A multi-valued neuron (MVN) is based on the principles of multiple-valued threshold logic over the field of the complex numbers. The most important properties of MVN are: the complex-valued weights, inputs and output coded by the kth roots of unity and the activation function, which maps the complex plane into the unit circle. MVN learning is reduced to the movement along the unit circle, it is based on a simple linear error correction rule and it does not require a derivative. It is shown that using a traditional architecture of multilayer feedforward neural network (MLF) and the high functionality of the MVN, it is possible to obtain a new powerful neural network. Its training does not require a derivative of the activation function and its functionality is higher than the functionality of MLF containing the same number of layers and neurons. These advantages of MLMVN are confirmed by testing using parity n, two spirals and “sonar” benchmarks and the Mackey–Glass time series prediction.