Complex-valued neurons with phase-dependent activation functions

Authors:
Igor Aizenberg
Affiliations:
Department of Computer Science, Texas A&M University-Texarkana, Texarkana, TX
Venue:
ICAISC'10 Proceedings of the 10th international conference on Artifical intelligence and soft computing: Part II
Year:
2010

Citing 9
Cited 2

Multi-Valued and Universal Binary Neurons: Theory, Learning and Applications

Multi-Valued and Universal Binary Neurons: Theory, Learning and Applications
Rotation-Invariant Image Association for Endoscopic Positional Identification Using Complex-Valued Associative Memories

IWANN '01 Proceedings of the 6th International Work-Conference on Artificial and Natural Neural Networks: Bio-inspired Applications of Connectionism-Part II
Multilayer Feedforward Neural Network Based on Multi-valued Neurons (MLMVN) and a Backpropagation Learning Algorithm

Soft Computing - A Fusion of Foundations, Methodologies and Applications
Complex-Valued Neural Networks (Studies in Computational Intelligence)

Complex-Valued Neural Networks (Studies in Computational Intelligence)
Solving the XOR and parity N problems using a single universal binary neuron

Soft Computing - A Fusion of Foundations, Methodologies and Applications - Special issue on BISCSE 2005 " Forging the Frontiers" Part II
Complex-valued multistate neural associative memory

IEEE Transactions on Neural Networks
Improving the capacity of complex-valued neural networks with a modified gradient descent learning rule

IEEE Transactions on Neural Networks
A new design method for the complex-valued multistate Hopfield associative memory

IEEE Transactions on Neural Networks
Blur Identification by Multilayer Neural Network Based on Multivalued Neurons

IEEE Transactions on Neural Networks

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
Letters: Blind sequence estimation of MPSK signals using dynamically driven recurrent neural networks

Neurocomputing

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we observe two artificial neurons with complex-valued weights. There are a multi-valued neuron and a universal binary neuron. Both neurons have activation functions depending on the argument (phase) of the weighted sum. A multi-valued neuron may learn multiple-valued threshold functions. A universal binary neuron may learn arbitrary (not only linearly-separable) Boolean functions. It is shown that a multi-valued neuron with a periodic activation function may learn non-threshold functions by their projection to the space corresponding to the larger valued logic. A feedforward neural network with multi-valued neurons and its learning are also considered.