Some special properties of GA and LS based neural learning method

Ranadhir Ghosh

School of Information Technology and Mathematical Sciences

University of Ballarat, PO Box 663

Ballarat – 3353, Australia

Abstract: There has been many works in the area of hybrid neural learning algorithms, which combine global and local based method for artificial neural network. In this paper, we discuss some special properties of a hybrid neural learning algorithm, which combines GA based method with least square based methods such as QR factorisation. We look at different types of learning properties of this new hybrid algorithm such as; time complexity, convergence property, stability of algorithm.