Title :
Legendre neural networks with multi input multi output system equations
Author :
Ali, Hazem H. ; Haweel, Mohammed T.
Author_Institution :
Commun. & Electron. Dept., Arab Acad. for Sci. & Technol., Cairo, Egypt
Abstract :
This paper investigates a new methodology and structure for the neural network (NN) to enhance nonlinear multi-input multi-output (MIMO) signal processing. The new methodology depends on Legendre series expansion for the input pattern vectors. The proposed structure employs a flat single layer of neurons with linear transfer functions. This eliminates the hidden layers, the sigmoid non-linear transfer functions and back-propagation commonly employed in the conventional NN. The orthogonality offered by Legendre series improves the convergence properties of the proposed Legendre neural network (LNN). The nonlinearity of Legendre series plays the rule of the sigmoid non-linear transfer functions in the conventional NN. The linear transfer functions adopted provide the proposed LNN with the great advantage of providing solid and explicit formulae relating the input and target pattern vectors for any MIMO system at any field. A fast and uniform multi input/output LMS Newton type adaptive algorithm has been explored for training the proposed LNN in an incremental mode. The employment and improved performance of the proposed LNN in the field of modelling/simulation are illustrated through simulation experiments.
Keywords :
Legendre polynomials; MIMO systems; learning (artificial intelligence); neural nets; series (mathematics); signal processing; vectors; LNN training; Legendre neural network; Legendre series expansion; MIMO signal processing; Newton type adaptive algorithm; backpropagation; linear transfer function; modelling-simulation field; multiinput multioutput system equation; neuron layer; pattern vector; sigmoid nonlinear transfer function; signal enhancement; Artificial neural networks; Biological neural networks; Convergence; Mathematical model; Neurons; Polynomials; Vectors; Legendre polynomials; modeling and simulation; neural networks; nonlinear systems;
Conference_Titel :
Computer Engineering & Systems (ICCES), 2012 Seventh International Conference on
Conference_Location :
Cairo
Print_ISBN :
978-1-4673-2960-6
DOI :
10.1109/ICCES.2012.6408490